{ "data": { "a": { "slug": "mistral-vibe-cli", "name": "Mistral Vibe CLI", "vendor": "Mistral AI", "vendorUrl": "https://docs.mistral.ai/vibe/code/cli/install-setup", "kind": "harness", "category": "agent-harnesses", "summary": "Mistral AI's open-source terminal coding agent. It runs Mistral's hosted models or any OpenAI-compatible endpoint, headless with `vibe -p` and in editors through `vibe-acp`. This listing covers the CLI, not Mistral's Vibe chat app.", "url": "https://www.anchorterminal.com/tools/mistral-vibe-cli", "markdownUrl": "https://www.anchorterminal.com/tools/mistral-vibe-cli.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mistral-vibe-cli.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mistral-vibe-cli.json", "dns": "mistral-vibe-cli.grade.anchorterminal.com", "repo": "https://github.com/mistralai/mistral-vibe", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "mistral-vibe" } ], "auth": "mixed", "authNotes": "Browser sign-in with a Mistral account, or a Mistral API key in `MISTRAL_API_KEY` or `~/.vibe/.env`, created under Code, Vibe CLI in the Mistral console. The same key works on the Free plan, a paid plan or pay-as-you-go. A local OpenAI-compatible server needs no Mistral account. MCP servers take static headers or OAuth.", "pricing": "freemium", "pricingNotes": "The CLI is free under Apache-2.0. Hosted models come with a Mistral plan or an API key. Free has limited coding sessions, Pro is $14.99 a month and Team $24.99 a user a month, Enterprise by quote, with pay-as-you-go at API rates past a plan's limit. The default model, Mistral Medium 3.5, is $1.5 per million input tokens and $7.5 per million output tokens on the API. A local model costs nothing (checked 2026-10-18).", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the CLI docs or the source (checked 2026-10-18).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 5100, "npmWeekly": null, "pypiWeekly": 331757, "asOf": "2026-10-18" }, "docsUrl": "https://docs.mistral.ai/vibe/code/cli/install-setup", "llmsTxt": "https://docs.mistral.ai/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "open-source", "python", "mcp", "acp", "llms-txt", "telemetry-default-on", "no-sandbox", "subagents", "hooks", "freemium", "no-card", "local" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 58.4, "grade": "C", "agentReady": false, "rank": 746, "ranked": true, "rankOf": 1486, "categoryRank": 21, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 84, "maintenance": 73, "payments": 60, "reliability": 69, "schema": 85, "security": 58, "transparency": 81 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -14, "negativeNotes": [ "2026-09-12. CVE-2026-87983 to CVE-2026-87988 (advisory MAI-2026-003, severity High, published 14 September 2026). Crafted shell commands could run without the approval prompt, reading or writing files outside the workspace or running code, and injected instructions could trigger them. HiddenLayer published the CVEs on 11 September and Mistral released 2.25.4 the next day. Fixed and published inside six months, so 2 points for each high (from 14 November each is a fixed High over two months old at 1, which still makes -6), as nanobot's and zeroclaw's fixed advisories were weighed. Six highs come to 12, held at the -6 cap for fixed and published advisories that claude-code and the Claude Agent SDK listing use (research/new/NOTES-harnesses-H1.md, negative events). Paperclip's -10 adds -5 for its group of ten fixed advisories and separate lines for advisories with no patched version, which doesn't apply here (https://docs.mistral.ai/resources/security-advisories/MAI-2026-003). -6", "2026-10-18. The offline guide says that with `enable_telemetry = false` and `enable_auto_update = false` the CLI contacts no external service, and the configuration reference describes `enable_auto_update` as installing releases in the background. The 2.26.1 source defines that key but nothing reads it, and the configuration reference now says it has no effect. Update checks follow `enable_update_checks`, which stays on, and the README says interactive sessions then query PyPI or uv once a day. We followed ironclaw's precedent, not zeroclaw's, because this is the vendor's documentation contradicting the shipped release on what leaves the machine, where zeroclaw's was a site-versus-docs mismatch. The safety page's line that `-p` falls back to `auto-approve` is also wrong, but it errs towards caution, so it stays a weakness with no deduction. A misleading claim, at the minimum, -2 (https://docs.mistral.ai/vibe/code/cli/offline-models; https://docs.mistral.ai/vibe/code/cli/configuration-reference; https://github.com/mistralai/mistral-vibe#update-settings). -2 On 2 November the offline guide, the configuration reference and the safety page agree with the source (`enable_update_checks`, and `-p` runs the default agent and denies calls needing approval). Corrected after our check with no note of the change, so the -2 is kept for the 12-month window, as supermemory's corrected claim was.", "2026-10-26. Patch releases 3.0.3 (26 October) and 3.0.4 (30 October) ship changes the changelog marks breaking for existing users. `auto_compact_threshold = 0` becomes a config error, the `compaction_thinking` setting is removed, a reply without token usage fails the turn so third-party model servers must support `stream_options.include_usage`, invalid or partial shell timeout settings are refused, and 3.0.4 stops loading custom Python tools and removes `tool_paths`. No pre-release or dated notice for the 3.0.3 breaks was found. 3.x, so the 0.x exemption doesn't reach them, and repeats fold into one term (https://github.com/mistralai/mistral-vibe/blob/main/CHANGELOG.md). -3", "2026-10-19. Released fixes of described flaws with no advisory. 3.0.0 says that on Windows the shell tools no longer auto-approve commands that hide part of the command from the approval check with a mid-word `#`, an escaped quote or PowerShell quoting, and 3.0.3 says creating a worktree no longer runs file filters from the repository's own Git configuration before the folder is trusted, and that automatic project context no longer runs repository-configured signature verification programs. Mistral's advisories page lists nothing after MAI-2026-003 (14 September) and OSV has no record for mistral-vibe. Release prose isn't an advisory, so one term (https://docs.mistral.ai/resources/security-advisories). -3" ], "verdict": "Apache-2.0 with releases most weeks, and headless runs capped by turns, tokens, price and wall time, with typed exit codes and an export file. File edits are auto-approved by default, the host has no sandbox, telemetry is on by default, and patch releases 3.0.3 and 3.0.4 shipped marked breaking changes.", "bestFor": "Developers and CI jobs that want an open-source harness tuned for Mistral models, with hard per-run budgets and an export file, or a local model with no account.", "strengths": [ "Apache-2.0, on PyPI and Homebrew at 3.0.4, with 21 release tags from 4 August to 30 October 2026", "`vibe -p` stops on `--max-turns`, `--max-tokens`, `--max-price` or `--time-limit`, with exit codes 0 to 4 and an `export.json` naming the outcome", "Runs against any OpenAI-compatible endpoint, with a llama.cpp provider on 127.0.0.1:8080 in the defaults and a documented offline set-up", "Project `.vibe/` config, hooks, MCP servers and `AGENTS.md` load only from trusted folders, and `-p` runs never trust a folder without `--trust`", "`vibe config schema` prints a JSON schema of every setting, and `strict_config` refuses unknown keys" ], "weaknesses": [ "The default agent auto-approves file edits, and there's no sandbox on the host. Isolation needs the experimental `--agent-socket` server or a container", "Six high-severity shell-permission bypasses (CVE-2026-87983 to CVE-2026-87988) were fixed in 2.25.4 on 12 September 2026, and later approval and Git-config fixes came with no advisory", "Patch releases 3.0.3 and 3.0.4 changed config, model-server and custom-tool behaviour the changelog marks as breaking", "Telemetry is on by default, and the server-side experiments it enables can switch the default agent to the `smart-approve` classifier", "The repository takes no outside contributions, and its history is squashed release commits" ], "agentNotes": [ "Pass `--agent` on every `-p` run (`plan` is read-only). The default is `accept-edits`, and an experiment can switch it to `smart-approve`", "Add `--max-turns`, `--max-tokens`, `--max-price` and `--time-limit`, and read `outcome` in the `export.json` that `--output-dir` writes. Exit 3 means a limit or a refusal", "Run in a container or behind `--agent-socket` before using `--auto-approve`, and set `outside_workdir = \"deny\"` to refuse paths outside the working directory", "For offline runs set `enable_telemetry = false` and `enable_update_checks = false` in `config.toml`", "Pin a version and read the changelog before upgrading, since patch releases can carry marked breaking changes; serve token usage from third-party model servers (`stream_options.include_usage`)" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.4 } ], "editorialScores": { "ergonomics": 84, "maintenance": 73, "payments": 60, "reliability": 69, "schema": 85, "security": 58, "transparency": 70 }, "provenanceScore": 91, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv tool install mistral-vibe # or: curl -LsSf https://mistral.ai/vibe/install.sh | bash", "headless": { "command": "vibe --prompt-file task.md --agent accept-edits --output json --max-turns 30 --max-price 1.0 --time-limit 1800 --output-dir out/", "env": { "MISTRAL_API_KEY": "\u003ckey\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/mistral-vibe-cli" }, "sameCompany": [ "mistral-api", "mistral-embeddings", "mistral-moderation", "mistral-voxtral-transcribe", "voxtral-mini-4b-realtime-2602", "mistral-ocr", "mistral-large-4" ], "area": "frameworks", "provenance": { "legalEntity": "Mistral AI (RCS Paris 952 418 325)", "domain": "mistral.ai", "domainRegistered": "2019-05-15", "endpointOnVendorDomain": null, "terms": "https://legal.mistral.ai/terms/commercial-terms-of-service", "privacy": "https://legal.mistral.ai/terms/privacy-policy", "statusPage": "https://status.mistral.ai", "changelog": "https://github.com/mistralai/mistral-vibe/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-11-02", "notes": [ "security.txt read on 2026-10-18, a Mistral security contact, Expires 2027-05-05, Policy a HackerOne submission form. SECURITY.md in the repository points to the same contact and programme", "Privacy policy effective 3 September 2026 and commercial terms effective 25 September 2026, both read on 2026-10-18. Both name Vibe among the Mistral AI products they cover", "The legal entity and domain date are carried from the mistral-api listing's 17 October check", "status.mistral.ai covers the hosted API and answers with a Cloudflare bot check, so it wasn't read (2 November, as the other Mistral listings). It doesn't cover the local CLI" ], "score": 91 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mistral-vibe-cli.json", "live": { "slug": "mistral-vibe-cli", "vendorStatus": { "page": "https://status.mistral.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:21:28.819228712Z" }, "versions": [ { "registry": "github", "name": "mistralai/mistral-vibe", "version": "v3.1.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:46:31.274882743Z" }, { "registry": "pypi", "name": "mistral-vibe", "version": "3.1.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:46:31.067374136Z" } ], "githubStars": 5318, "pypiWeekly": 537852, "securityTxt": { "url": "https://mistral.ai/.well-known/security.txt", "state": "valid", "expires": "2027-05-05T23:59:59.000Z", "checkedAt": "2026-11-07T16:00:05.953035328Z" }, "llmsTxt": { "url": "https://docs.mistral.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:15.385904897Z" }, "domain": { "domain": "mistral.ai", "registered": "2019-05-15", "source": "https://rdap.identitydigital.services/rdap/domain/mistral.ai", "checkedAt": "2026-11-01T14:21:43.304217994Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/mistralai/mistral-vibe/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:21:49.923529798Z", "changedAt": "2026-11-04T08:34:10.317029578Z", "fingerprint": "5cf56aa860c5" } ], "github": { "repo": "mistralai/mistral-vibe", "checkedAt": "2026-11-02T09:07:45.565868424Z", "stars": 5271, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T11:03:02Z", "openIssues": 245, "openPRs": 203, "issuesOpened90d": 239, "issuesClosed90d": 175, "prsMerged90d": 26, "ci": { "branch": "main", "runs": 50, "success": 40, "failure": 10, "other": 0, "latest": "success", "latestAt": "2026-10-30T11:25:05Z" }, "replies": { "sampled": 25, "unanswered": 21, "medianDays": 0.1 } }, "updatedAt": "2026-11-07T18:21:28.819228712Z" } }, "answer": "Mistral Vibe CLI scores 58.4 (C) on agent readiness against Verdent's 39.7 (E), and leads in every scored category.", "b": { "slug": "verdent", "name": "Verdent", "vendor": "Verdent AI, Inc.", "vendorUrl": "https://www.verdent.ai", "kind": "harness", "category": "agent-harnesses", "summary": "Verdent is a coding agent from Verdent AI, Inc., with a desktop app for macOS and Windows, VS Code and JetBrains extensions and a browser edition. It plans tasks, runs parallel workers in git worktrees and uses MCP servers.", "url": "https://www.anchorterminal.com/tools/verdent", "markdownUrl": "https://www.anchorterminal.com/tools/verdent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/verdent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/verdent.json", "dns": "verdent.grade.anchorterminal.com", "license": "Proprietary. The terms of use from Verdent AI, Inc. forbid reverse engineering or copying any component, and no source is published", "transports": [], "packages": [], "auth": "mixed", "authNotes": "A person signs in to a Verdent account with Google, GitHub or email in a browser. Model use runs on Verdent credits through llm-proxy.verdent.ai, or on the user's own Anthropic, OpenAI or OpenRouter key (BYOK). BYOA runs workers on a local Claude Code or Codex CLI with keys kept on the machine. No API key or token for driving Verdent from another program was found.", "pricing": "paid", "pricingNotes": "From $5 a month (Lite), then $19 Starter, $59 Pro and $179 Max with 320, 1,000 and 3,000 credits a month (doubled by a limited-time bonus). One credit is about $0.059 at provider rates. Top-ups $20 for 340 credits to $200 for 3,400. Free Mode and the free trial ended with v2.18.0 on 29 October 2026.", "priceSummary": "$5 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, pricing page, terms or changelog (checked 2026-11-06). Subscriptions and top-ups go through Stripe.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://www.verdent.ai/docs/verdent-manager/getting-started/overview", "capabilities": [ "agent.harness", "agent.multi-agent", "agent.mcp-client" ], "tags": [ "official", "harness", "coding-agent", "closed-source", "desktop", "vscode", "jetbrains", "mcp", "byok", "paid-plans", "no-sandbox" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 39.7, "grade": "E", "agentReady": false, "rank": 1317, "ranked": true, "rankOf": 1486, "categoryRank": 53, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 35, "maintenance": 61, "payments": 20, "reliability": 43, "schema": 55, "security": 33, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -2, "negativeNotes": [ "2026-11-06. The changelog says v2.18.0 of 29 October 2026 retired Free Mode, the free trial and the 100 welcome credits, while the pricing page FAQ read on 6 November still says \"Your free trial includes 100 credits\" and the 1.0 docs overview still lists a free trial. A stale claim on the vendor's own pricing page, 2 points. https://www.verdent.ai/pricing, https://www.verdent.ai/changelog" ], "verdict": "A desktop and editor coding agent that splits a goal into parallel workers in git worktrees, with a read-only Plan Mode, MCP servers and the option to run workers on Claude Code or Codex. It has no CLI, API or sandbox, sends context through Verdent's servers, and has had no free tier since 29 October 2026.", "bestFor": "A person who wants a desktop app to plan and run several coding tasks at once, possibly on their own Claude Code or Codex.", "strengths": [ "Plan Mode is read-only and writes a plan.md for review before Agent Mode makes changes", "Parallel workers each run in their own git worktree, with a review column before work is accepted", "BYOA runs workers on a local Claude Code or Codex CLI, and BYOK takes Anthropic, OpenAI or OpenRouter keys", "Plan, top-up and per-credit prices are public, charged at provider token rates with no markup per the pricing page", "Every current docs page has a Markdown twin, and the changelog is dated by version" ], "weaknesses": [ "No CLI, print mode, API or SDK, so a pipeline can't start or read a run except through a paired chat bot", "No sandbox or network restriction documented, and the actions that need approval aren't listed", "Free Mode and the free trial ended on 29 October 2026, while the pricing page FAQ still promises 100 trial credits", "Event logging to log.verdent.ai has no documented opt-out, and the privacy policy gives no retention periods", "SOC 2 and ISO/IEC 42001 are being pursued, not held, and there is no bug bounty or security.txt" ], "agentNotes": [ "Don't plan to drive Verdent headless. Hand the task to the person using the desktop app, or use a harness with a print mode", "Start large changes in Plan Mode and review plan.md before switching to Agent Mode", "Add MCP servers in the project's .mcp.json or ~/.verdent/mcp.json in the mcpServers shape", "Keep work under git, since rollback relies on git and there is no sandbox", "Budget in credits at about $0.059 each, because there is no free allowance since 29 October 2026" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 39.7 } ], "editorialScores": { "ergonomics": 35, "maintenance": 61, "payments": 20, "reliability": 43, "schema": 55, "security": 33, "transparency": 47 }, "provenanceScore": 62, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "config": { "mcpServers": { "github": { "args": [ "-y", "@modelcontextprotocol/server-github" ], "command": "npx", "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}" } } } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/verdent" }, "area": "frameworks", "unitPrices": [ { "item": "Lite plan", "unit": "month", "usd": 5, "note": "Eco Mode models and light usage" }, { "item": "Starter plan", "unit": "month", "usd": 19, "note": "320 credits a month, 480 with the limited-time bonus" }, { "item": "Pro plan", "unit": "month", "usd": 59, "note": "1,000 credits a month, 1,500 with the bonus" }, { "item": "Max plan", "unit": "month", "usd": 179, "note": "3,000 credits a month, 4,500 with the bonus" }, { "item": "Credit", "unit": "credit", "usd": 0.059, "note": "About $0.059, charged at provider token prices with no markup per the pricing page" } ], "provenance": { "legalEntity": "Verdent AI, Inc.", "domain": "verdent.ai", "domainRegistered": "2025-05-06", "endpointOnVendorDomain": true, "terms": "https://www.verdent.ai/terms", "privacy": "https://www.verdent.ai/privacy", "statusPage": "", "changelog": "https://www.verdent.ai/changelog", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The privacy policy names Verdent AI, Inc. as data controller, and the terms choose California law.", "The terms forbid users to crawl, scrape or otherwise harvest data or information from the Services. Public pages were read once each.", "www.verdent.ai/robots.txt allows all crawlers.", "RDAP gives verdent.ai a registration date of 6 May 2025.", "/.well-known/security.txt returns 404, and status.verdent.ai did not answer. No status page found.", "The security page says SOC 2 and ISO/IEC 42001 are being pursued, not held, and takes vulnerability reports at hi@verdent.ai with acknowledgement within five business days." ], "score": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/verdent.json", "live": { "slug": "verdent", "securityTxt": { "url": "https://verdent.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:33.272105482Z" }, "pages": [ { "url": "https://www.verdent.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:36:28.662063151Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "bac05e4e426e" }, { "url": "https://www.verdent.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:36:31.354667853Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3ec1d3c07d70" }, { "url": "https://www.verdent.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:36:33.295376926Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "206b6ec23a6a" } ], "updatedAt": "2026-11-07T15:59:33.272105482Z" } }, "edges": [ { "by": 49, "category": "ergonomics", "leads": "mistral-vibe-cli", "name": "Agent ergonomics", "reasons": { "a": "Framework reading, adapted to a harness driven by a pipeline. `--enabled-tools` and `--disabled-tools` with globs and regex (in `-p` the first disables everything else), per-tool and per-MCP-tool permissions, and switches for subagents and background processes (20 of 25). `--max-turns`, `--max-tokens`, `--max-price` and `--time-limit`, with text, json and streaming output and an export file with usage and cost (20). Exit codes 0 to 4 with named outcomes, refusals reported with a code, and config problems listed under `warnings` (18). `--resume SESSION_ID` and `--continue`, SIGTERM stops a run so it can be resumed, and model API failures are retried before exit 2 (16). One required input (the prompt), a GitHub Action and the ACP server, but no SDK, and the app-server's JSON-RPC protocol isn't documented for outside use (10). 20+20+18+16+10 = 84.", "b": "Harness reading. MCP servers per project or globally, subagents, skills and rules, but no per-tool disabling or deferred loading found (10). No output-size, turn-limit or budget controls for a run were found beyond credit balances (5). No exit codes or error format, since there is no headless mode (3). Parallel workers in git worktrees and a review column make runs reviewable and reversible, with no resume by ID documented (10). No CLI, API or SDK. A pipeline can only reach Manager through a paired Telegram, Slack or Feishu bot (7). 10+5+3+10+7 = 35." }, "scores": { "a": 84, "b": 35 } }, { "by": 40, "category": "payments", "leads": "mistral-vibe-cli", "name": "Payments \u0026 pricing", "reasons": { "a": "Harness reading of the published rubric, as for openai-codex and qwen-code. No payment protocol (0). Plan prices (Pro $14.99 a month, Team $24.99 a user a month) and per-token API prices for the default model ($1.5 and $7.5 per million) are public without a login (20). A Free plan includes limited coding sessions, and the docs document a fully offline set-up with a local model and no Mistral account. Whether the Free plan asks for a card wasn't checked (20). An agent can install the CLI and run it against a local OpenAI-compatible server with no sign-up, since a llama.cpp provider on 127.0.0.1:8080 is in the defaults (20). 0+20+20+20 = 60.", "b": "Harness reading of the published rubric, scored on the Verdent subscription the agent needs. No payment protocol (0). Plan prices from $5 a month, top-up prices and the credit value of about $0.059 are public without a login (20). Free Mode and the free trial ended on 29 October 2026, so there is no free tier (0). A person signs up in a browser (0). 0+20+0+0 = 20." }, "scores": { "a": 60, "b": 20 } }, { "by": 30, "category": "schema", "leads": "mistral-vibe-cli", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. A configuration reference with each key's type and default, the `export.json` fields, and the `--agent-socket` JSON-RPC methods with typed params and results in the README, plus ACP. Since 3.0.3 `vibe config schema` prints a JSON schema of every setting, including each built-in tool's; the streaming events still have no published schema (20 of 25). docs.mistral.ai/llms.txt indexes the CLI pages, each with a Markdown twin (10). The safety page says what each agent allows and when to use it, and on 2 November it agrees with the source. `-p` runs the configured `default_agent` and denies calls that need approval, and the offline guide and configuration reference name `enable_update_checks`. The 18 October contradictions and TODO notes are gone (15 of 20). Output formats, agent names, permission values and OpenTelemetry redaction modes are enums, and the config is validated on load (12). Many examples and an exit-code table that maps each code to the outcome names in `export.json` (13). Dated changelog and version tags (15). 20+10+15+12+13+15 = 85.", "b": "Framework reading for a harness. No schema for settings or output, only mcp.json examples in the standard mcpServers shape (5). Every current docs page has a Markdown twin at the same path with .md, though no llms.txt (10). The docs say when to use Agent Mode or Plan Mode and what Plan Mode can't do, but the Agent Mode page lists the actions that need approval only as \"certain tool executions\" and \"destructive operations\" (12). Modes and BYOA agent types are enumerated, permissions are not (5). Examples on the MCP, BYOA and messaging pages, and a recovery page, with no error codes (8). Version numbers and a dated public changelog (15). The archived 1.0 docs are still served beside the current ones. 5+10+12+5+8+15 = 55." }, "scores": { "a": 85, "b": 55 } }, { "by": 26, "category": "reliability", "leads": "mistral-vibe-cli", "name": "Reliability", "reasons": { "a": "Local-package reading. PyPI, uv, pip, Homebrew at 3.0.4 and an install script, with Python 3.12 or later stated and UNIX the supported target (20). A public CI workflow on push and pull request to main runs pre-commit, the test suite and a build and install smoke matrix, but GitHub's pages and API were refused in this session, so whether main is passing is unchecked (15 of 25). The 18 October issue counts came from shields.io badges, a third-party copy of GitHub data this run bars, so they are struck. Every release has a Fixed section in the changelog, and how many open issues are crashes or regressions, and how fast they're answered, couldn't be read (10 of 25). The changelog states Keep a Changelog and semver and marks breaking changes, but the hooks rename shipped in minor 2.21.0, patch 2.11.1 changed the `-p` approval default, patch 2.26.1 removed the bundled local model, and patches 3.0.3 and 3.0.4 carry marked config, model and session breaks (9). 3.0.4, classified Production/Stable (15). 20+15+10+9+15 = 69.", "b": "Local-package reading, as for the other closed-source harnesses. The desktop app installs from verdent.ai with macOS 11 or later and 64-bit Windows 10 and 11 stated, and the extension from the editor marketplaces, but not from a package registry (15). No public CI or test suite, since the source isn't published (0). No public issue tracker, every task runs through Verdent's servers, and no status page was found, so there is no readable record (5). A dated changelog by version, with the end of Free Mode called out in v2.18.0, but no breaking-change sections (8). 2.18.0, generally available (15). 15+0+5+8+15 = 43." }, "scores": { "a": 69, "b": 43 } }, { "by": 26, "category": "transparency", "leads": "mistral-vibe-cli", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache-2.0, with LICENSE and pyproject in agreement (30). The README sends readers to Mistral's privacy policy (effective 3 September 2026), which names Vibe. The commercial terms (effective 25 September 2026) say no training on customer data unless a product's default or an opt-in allows it, and the pricing page lists model training as opt-out on Free, Pro and Team. The configuration reference calls telemetry anonymous without listing its fields. The offline guide now names `enable_update_checks = false` with `enable_telemetry = false`, as the source reads them (16 of 30; 14 on 18 October, when it named a key the source defines but never reads). Removals are listed in the changelog, deprecated settings are named in the configuration reference and warned about at startup, the agent socket may change without notice, and custom Python tools and the bundled local model were removed in patch releases with warnings (10 of 20). Telemetry is disclosed with an opt-out in the README and the configuration reference, and the README names the server-managed shell-tool rollout, but its fields are only in the source (14 of 20). 30+16+10+14 = 70.", "b": "Proprietary, under terms from Verdent AI, Inc. that are clear on use and ownership (15). The privacy policy and security page agree that data stays in the US and that input isn't trained on without consent, and the security page lists subprocessors. The privacy policy gives no retention periods, names MiniMax as a provider the security list leaves out, and deletion is by email request (14). The credit bonus carries a promise of 15 days' notice, but Free Mode was retired on the day v2.18.0 shipped and no deprecation policy was found (6). Subprocessors and their locations are listed, and the domains the app calls are named, with event logging undescribed (12). 15+14+6+12 = 47." }, "scores": { "a": 81, "b": 55 } }, { "by": 25, "category": "security", "leads": "mistral-vibe-cli", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Telemetry and crash reporting are on by default with an opt-out, and the source sends tool names, approval decisions, the model and file counts to api.mistral.ai only when a Mistral key is set. Telemetry also turns on GrowthBook experiments, and one of them (`vibe_cli_smart_approve_default`) can make smart-approve the default. Credentials are Mistral keys in an environment variable, a plaintext `~/.vibe/.env` or the keyring, workspace-scoped with optional expiry per the mistral-api listing, and MCP servers can use OAuth (12 of 30). Five agents with a read-only plan agent and bash allow and deny lists, a prompt for access outside the working directory, `outside_workdir = \"deny\"` (3.0.3) to refuse it outright, an admin `enable_auto_approve = false` (3.0.1) that forbids auto-approve, and `pre_tool` hooks that can deny calls. The default auto-approves file edits, and there's no sandbox on the host (13 of 20; 11 on 18 October, before the two settings). Project config, hooks and MCP servers load only from trusted folders, and `-p` needs `--trust` to load them. The safety page warns that smart-approve isn't a sandbox. No network egress control on the host, and MAI-2026-003 says injected instructions could trigger the bypassed commands (8 of 15). OpenTelemetry tracing is opt-in, with default, strict and no redaction, and each run can write a session journal and an export with the effective config. Managed admin config exists, and audit logs come with the Enterprise plan (13). SECURITY.md asks for private reports, security.txt is valid (expires 5 May 2027) and links a HackerOne form, and Mistral publishes dated advisories with CVEs, three to 2 November. No bounty terms or certification report were read, so 12, as mistral-api and mistral-voxtral-transcribe take on the same Mistral pages (14 on 18 October). 12+13+8+13+12 = 58.", "b": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing). Conversation history and tool results go to Verdent's US servers and on to Azure, Bedrock or Vertex, with zero data retention stated for Vertex and Bedrock only. Event logging to log.verdent.ai has no documented opt-out. BYOA keys stay on the machine (10). Plan Mode is read-only, Agent Mode asks before destructive commands and edits outside scope, and workers are isolated by git worktree, but there is no sandbox or network control and the approval list isn't enumerated (9). No prompt-injection guidance found, while web search and fetch results enter the context (2). Usage history in the dashboard, no audit log found (5). A security page with a disclosure address and a five-day acknowledgement, SOC 2 and ISO/IEC 42001 being pursued rather than held, no security.txt and no bug bounty (7). 10+9+2+5+7 = 33." }, "scores": { "a": 58, "b": 33 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Mistral AI", "b": "Verdent AI, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Paid", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Proprietary. The terms of use from Verdent AI, Inc. forbid reverse engineering or copying any component, and no source is published", "name": "Licence" }, { "a": "yes", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-29", "name": "Last release" }, { "a": "2026-09-25", "b": "2026-05-25", "name": "Terms last updated" }, { "a": "2026-09-03", "b": "2026-05-26", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "yes", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "5.1k stars, 332k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Mistral Vibe CLI scores 58.4 (C) on agent readiness against Verdent's 39.7 (E), and leads in every scored category.", "question": "Which is better for AI agents, Mistral Vibe CLI or Verdent?" }, { "answer": "Mistral Vibe CLI is open source (Apache-2.0). No open-source release is listed for Verdent.", "question": "Are Mistral Vibe CLI and Verdent open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 69 against 43", "Schema \u0026 documentation, 85 against 55", "Agent ergonomics, 84 against 35", "Security \u0026 auth, 58 against 33", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 73 against 61", "Transparency \u0026 trust, 81 against 55" ], "also": [ "Free to start without a card", "Open source" ], "goodFor": "Developers and CI jobs that want an open-source harness tuned for Mistral models, with hard per-run budgets and an export file, or a local model with no account.", "slug": "mistral-vibe-cli", "watchFor": "The default agent auto-approves file edits, and there's no sandbox on the host. Isolation needs the experimental `--agent-socket` server or a container" }, { "aheadOn": null, "also": null, "goodFor": "A person who wants a desktop app to plan and run several coding tasks at once, possibly on their own Claude Code or Codex.", "slug": "verdent", "watchFor": "No CLI, print mode, API or SDK, so a pipeline can't start or read a run except through a paired chat bot" } ], "history": { "mistral-vibe-cli": [ { "causes": [ "product", "correction", "event" ], "date": "2026-11-02", "delta": -4.6, "from": 63, "fromGrade": "B", "to": 58.4, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 62.9, "fromGrade": "B", "to": 63, "toGrade": "B" } ], "verdent": null }, "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli.json", "title": "Agent Zero vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-verdent.json", "title": "Agent Zero vs Verdent", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-mistral-vibe-cli.json", "title": "Aider vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-verdent.json", "title": "Aider vs Verdent", "url": "https://www.anchorterminal.com/compare/aider-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-mistral-vibe-cli.json", "title": "Amp vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/amp-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-verdent.json", "title": "Amp vs Verdent", "url": "https://www.anchorterminal.com/compare/amp-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-mistral-vibe-cli.json", "title": "Antigravity CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-verdent.json", "title": "Antigravity CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-mistral-vibe-cli.json", "title": "Auggie CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/auggie-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-verdent.json", "title": "Auggie CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/auggie-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli.json", "title": "AXLR vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-verdent.json", "title": "AXLR vs Verdent", "url": "https://www.anchorterminal.com/compare/axlr-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli.json", "title": "Claude Code vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-verdent.json", "title": "Claude Code vs Verdent", "url": "https://www.anchorterminal.com/compare/claude-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-mistral-vibe-cli.json", "title": "Cline vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/cline-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-verdent.json", "title": "Cline vs Verdent", "url": "https://www.anchorterminal.com/compare/cline-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-mistral-vibe-cli.json", "title": "Conductor vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/conductor-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-verdent.json", "title": "Conductor vs Verdent", "url": "https://www.anchorterminal.com/compare/conductor-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli.json", "title": "Crush vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-verdent.json", "title": "Crush vs Verdent", "url": "https://www.anchorterminal.com/compare/crush-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-mistral-vibe-cli.json", "title": "Cursor CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-verdent.json", "title": "Cursor CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli.json", "title": "DeepSeek Harness (dsh) vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-verdent.json", "title": "DeepSeek Harness (dsh) vs Verdent", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli.json", "title": "dsh-superagent (DeepSeek) vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-verdent.json", "title": "dsh-superagent (DeepSeek) vs Verdent", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-mistral-vibe-cli.json", "title": "Devin vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-verdent.json", "title": "Devin vs Verdent", "url": "https://www.anchorterminal.com/compare/devin-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-mistral-vibe-cli.json", "title": "Droid CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-verdent.json", "title": "Droid CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli.json", "title": "Pi vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-verdent.json", "title": "Pi vs Verdent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli.json", "title": "Emdash vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-verdent.json", "title": "Emdash vs Verdent", "url": "https://www.anchorterminal.com/compare/emdash-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli.json", "title": "Gemini CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-verdent.json", "title": "Gemini CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-mistral-vibe-cli.json", "title": "GitHub Copilot CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-verdent.json", "title": "GitHub Copilot CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-mistral-vibe-cli.json", "title": "goose vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/goose-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-verdent.json", "title": "goose vs Verdent", "url": "https://www.anchorterminal.com/compare/goose-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.json", "title": "Harness² vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-verdent.json", "title": "Harness² vs Verdent", "url": "https://www.anchorterminal.com/compare/harness2-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli.json", "title": "HarnessRouter vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-verdent.json", "title": "HarnessRouter vs Verdent", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli.json", "title": "Jules vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-verdent.json", "title": "Jules vs Verdent", "url": "https://www.anchorterminal.com/compare/jules-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-mistral-vibe-cli.json", "title": "Junie CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/junie-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-verdent.json", "title": "Junie CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/junie-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-mistral-vibe-cli.json", "title": "Kilo Code CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-verdent.json", "title": "Kilo Code CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-mistral-vibe-cli.json", "title": "Kimi Code CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-verdent.json", "title": "Kimi Code CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-mistral-vibe-cli.json", "title": "Kiro CLI vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-verdent.json", "title": "Kiro CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/letta-vs-mistral-vibe-cli.json", "title": "Letta vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/letta-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/letta-vs-verdent.json", "title": "Letta vs Verdent", "url": "https://www.anchorterminal.com/compare/letta-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-mistral-vibe-cli.json", "title": "mini-swe-agent vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-verdent.json", "title": "mini-swe-agent vs Verdent", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-mistral-vibe-cli.json", "title": "MiniMax Code vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-verdent.json", "title": "MiniMax Code vs Verdent", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-muse-code.json", "title": "Mistral Vibe CLI vs Muse Code", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api.json", "title": "Mistral Vibe CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-codex.json", "title": "Mistral Vibe CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-opencode.json", "title": "Mistral Vibe CLI vs OpenCode", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openhands.json", "title": "Mistral Vibe CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openmausbot.json", "title": "Mistral Vibe CLI vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca.json", "title": "Mistral Vibe CLI vs Orca", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paseo.json", "title": "Mistral Vibe CLI vs Paseo", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paseo" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-prime-agent.json", "title": "Mistral Vibe CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qoder-cli.json", "title": "Mistral Vibe CLI vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qwen-code.json", "title": "Mistral Vibe CLI vs Qwen Code", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-reflection-mirror.json", "title": "Mistral Vibe CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-rovo-dev-cli.json", "title": "Mistral Vibe CLI vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor.json", "title": "Mistral Vibe CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code.json", "title": "Mistral Vibe CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-traycer.json", "title": "Mistral Vibe CLI vs Traycer", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-unstoppable.json", "title": "Mistral Vibe CLI vs Unstoppable", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-vibe-trading.json", "title": "Mistral Vibe CLI vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp.json", "title": "Mistral Vibe CLI vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-verdent.json", "title": "Muse Code vs Verdent", "url": "https://www.anchorterminal.com/compare/muse-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-verdent.json", "title": "OpenAI Agents API vs Verdent", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-verdent.json", "title": "OpenAI Codex vs Verdent", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-verdent.json", "title": "OpenCode vs Verdent", "url": "https://www.anchorterminal.com/compare/opencode-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-verdent.json", "title": "OpenHands vs Verdent", "url": "https://www.anchorterminal.com/compare/openhands-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-verdent.json", "title": "Orca vs Verdent", "url": "https://www.anchorterminal.com/compare/orca-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/paseo-vs-verdent.json", "title": "Paseo vs Verdent", "url": "https://www.anchorterminal.com/compare/paseo-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-verdent.json", "title": "Prime Agent vs Verdent", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/qoder-cli-vs-verdent.json", "title": "Qoder CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/qoder-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/qwen-code-vs-verdent.json", "title": "Qwen Code vs Verdent", "url": "https://www.anchorterminal.com/compare/qwen-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/reflection-mirror-vs-verdent.json", "title": "Mirror CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/reflection-mirror-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-verdent.json", "title": "Rovo Dev CLI vs Verdent", "url": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-verdent.json", "title": "Sculptor vs Verdent", "url": "https://www.anchorterminal.com/compare/sculptor-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-verdent.json", "title": "T3 Code vs Verdent", "url": "https://www.anchorterminal.com/compare/t3-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/traycer-vs-verdent.json", "title": "Traycer vs Verdent", "url": "https://www.anchorterminal.com/compare/traycer-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/verdent-vs-vibe-trading.json", "title": "Verdent vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/verdent-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/verdent-vs-warp.json", "title": "Verdent vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/verdent-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-mistral-vibe-cli.json", "title": "Clawboo vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/clawboo-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-verdent.json", "title": "Clawboo vs Verdent", "url": "https://www.anchorterminal.com/compare/clawboo-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-mistral-vibe-cli.json", "title": "CLI Manager vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-verdent.json", "title": "CLI Manager vs Verdent", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-mistral-vibe-cli.json", "title": "Harness vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-verdent.json", "title": "Harness vs Verdent", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paperclip.json", "title": "Mistral Vibe CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-parallax-agents.json", "title": "Mistral Vibe CLI vs Parallax", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-parallax-agents" }, { "json": "https://www.anchorterminal.com/compare/openmausbot-vs-verdent.json", "title": "OpenMausBot vs Verdent", "url": "https://www.anchorterminal.com/compare/openmausbot-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-verdent.json", "title": "Paperclip vs Verdent", "url": "https://www.anchorterminal.com/compare/paperclip-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-verdent.json", "title": "Parallax vs Verdent", "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/unstoppable-vs-verdent.json", "title": "Unstoppable vs Verdent", "url": "https://www.anchorterminal.com/compare/unstoppable-vs-verdent" } ], "panel": null, "scores": [ { "by": 26, "edge": "mistral-vibe-cli", "key": "reliability", "mistral-vibe-cli": 69, "name": "Reliability", "verdent": 43, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 30, "edge": "mistral-vibe-cli", "key": "schema", "mistral-vibe-cli": 85, "name": "Schema \u0026 documentation", "verdent": 55, "weight": 13 }, { "by": 49, "edge": "mistral-vibe-cli", "key": "ergonomics", "mistral-vibe-cli": 84, "name": "Agent ergonomics", "verdent": 35, "weight": 13 }, { "by": 25, "edge": "mistral-vibe-cli", "key": "security", "mistral-vibe-cli": 58, "name": "Security \u0026 auth", "verdent": 33, "weight": 14 }, { "by": 40, "edge": "mistral-vibe-cli", "key": "payments", "mistral-vibe-cli": 60, "name": "Payments \u0026 pricing", "verdent": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 12, "edge": "mistral-vibe-cli", "key": "maintenance", "mistral-vibe-cli": 73, "name": "Maintenance \u0026 community", "verdent": 61, "weight": 7 }, { "by": 26, "edge": "mistral-vibe-cli", "key": "transparency", "mistral-vibe-cli": 81, "name": "Transparency \u0026 trust", "verdent": 55, "weight": 7 } ], "summary": "Mistral Vibe CLI scores 58.4 (C) on agent readiness against Verdent's 39.7 (E), and leads in every scored category. Both do agent harnesses.", "tasks": null, "tutorials": [], "verdicts": { "mistral-vibe-cli": "Apache-2.0 with releases most weeks, and headless runs capped by turns, tokens, price and wall time, with typed exit codes and an export file. File edits are auto-approved by default, the host has no sandbox, telemetry is on by default, and patch releases 3.0.3 and 3.0.4 shipped marked breaking changes.", "verdent": "A desktop and editor coding agent that splits a goal into parallel workers in git worktrees, with a read-only Plan Mode, MCP servers and the option to run workers on Claude Code or Codex. It has no CLI, API or sandbox, sends context through Verdent's servers, and has had no free tier since 29 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent", "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent.min.md" }, "markdown": "Mistral Vibe CLI scores 58.4 (C) on agent readiness against Verdent's 39.7 (E), and leads in every scored category. Both do agent harnesses.\n\n- Mistral Vibe CLI: grade C, 58.4/100, rank #746 of 1486. Markdown https://www.anchorterminal.com/tools/mistral-vibe-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/mistral-vibe-cli.json\n- Verdent: grade E, 39.7/100, rank #1317 of 1486. Markdown https://www.anchorterminal.com/tools/verdent.md · JSON https://www.anchorterminal.com/api/v1/tools/verdent.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Mistral Vibe CLI (C)\n\nGood for: Developers and CI jobs that want an open-source harness tuned for Mistral models, with hard per-run budgets and an export file, or a local model with no account.\n\nAhead on:\n- Reliability, 69 against 43\n- Schema \u0026 documentation, 85 against 55\n- Agent ergonomics, 84 against 35\n- Security \u0026 auth, 58 against 33\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 73 against 61\n- Transparency \u0026 trust, 81 against 55\n\nAlso in its favour:\n- Free to start without a card\n- Open source\n\nWatch for: The default agent auto-approves file edits, and there's no sandbox on the host. Isolation needs the experimental `--agent-socket` server or a container\n\n### Verdent (E)\n\nGood for: A person who wants a desktop app to plan and run several coding tasks at once, possibly on their own Claude Code or Codex.\n\nWatch for: No CLI, print mode, API or SDK, so a pipeline can't start or read a run except through a paired chat bot\n\n\n## Why the edge\n\n### Agent ergonomics: Mistral Vibe CLI +49\n\n- Mistral Vibe CLI (84): Framework reading, adapted to a harness driven by a pipeline. `--enabled-tools` and `--disabled-tools` with globs and regex (in `-p` the first disables everything else), per-tool and per-MCP-tool permissions, and switches for subagents and background processes (20 of 25). `--max-turns`, `--max-tokens`, `--max-price` and `--time-limit`, with text, json and streaming output and an export file with usage and cost (20). Exit codes 0 to 4 with named outcomes, refusals reported with a code, and config problems listed under `warnings` (18). `--resume SESSION_ID` and `--continue`, SIGTERM stops a run so it can be resumed, and model API failures are retried before exit 2 (16). One required input (the prompt), a GitHub Action and the ACP server, but no SDK, and the app-server's JSON-RPC protocol isn't documented for outside use (10). 20+20+18+16+10 = 84.\n- Verdent (35): Harness reading. MCP servers per project or globally, subagents, skills and rules, but no per-tool disabling or deferred loading found (10). No output-size, turn-limit or budget controls for a run were found beyond credit balances (5). No exit codes or error format, since there is no headless mode (3). Parallel workers in git worktrees and a review column make runs reviewable and reversible, with no resume by ID documented (10). No CLI, API or SDK. A pipeline can only reach Manager through a paired Telegram, Slack or Feishu bot (7). 10+5+3+10+7 = 35.\n\n### Payments \u0026 pricing: Mistral Vibe CLI +40\n\n- Mistral Vibe CLI (60): Harness reading of the published rubric, as for openai-codex and qwen-code. No payment protocol (0). Plan prices (Pro $14.99 a month, Team $24.99 a user a month) and per-token API prices for the default model ($1.5 and $7.5 per million) are public without a login (20). A Free plan includes limited coding sessions, and the docs document a fully offline set-up with a local model and no Mistral account. Whether the Free plan asks for a card wasn't checked (20). An agent can install the CLI and run it against a local OpenAI-compatible server with no sign-up, since a llama.cpp provider on 127.0.0.1:8080 is in the defaults (20). 0+20+20+20 = 60.\n- Verdent (20): Harness reading of the published rubric, scored on the Verdent subscription the agent needs. No payment protocol (0). Plan prices from $5 a month, top-up prices and the credit value of about $0.059 are public without a login (20). Free Mode and the free trial ended on 29 October 2026, so there is no free tier (0). A person signs up in a browser (0). 0+20+0+0 = 20.\n\n### Schema \u0026 documentation: Mistral Vibe CLI +30\n\n- Mistral Vibe CLI (85): Framework reading. A configuration reference with each key's type and default, the `export.json` fields, and the `--agent-socket` JSON-RPC methods with typed params and results in the README, plus ACP. Since 3.0.3 `vibe config schema` prints a JSON schema of every setting, including each built-in tool's; the streaming events still have no published schema (20 of 25). docs.mistral.ai/llms.txt indexes the CLI pages, each with a Markdown twin (10). The safety page says what each agent allows and when to use it, and on 2 November it agrees with the source. `-p` runs the configured `default_agent` and denies calls that need approval, and the offline guide and configuration reference name `enable_update_checks`. The 18 October contradictions and TODO notes are gone (15 of 20). Output formats, agent names, permission values and OpenTelemetry redaction modes are enums, and the config is validated on load (12). Many examples and an exit-code table that maps each code to the outcome names in `export.json` (13). Dated changelog and version tags (15). 20+10+15+12+13+15 = 85.\n- Verdent (55): Framework reading for a harness. No schema for settings or output, only mcp.json examples in the standard mcpServers shape (5). Every current docs page has a Markdown twin at the same path with .md, though no llms.txt (10). The docs say when to use Agent Mode or Plan Mode and what Plan Mode can't do, but the Agent Mode page lists the actions that need approval only as \"certain tool executions\" and \"destructive operations\" (12). Modes and BYOA agent types are enumerated, permissions are not (5). Examples on the MCP, BYOA and messaging pages, and a recovery page, with no error codes (8). Version numbers and a dated public changelog (15). The archived 1.0 docs are still served beside the current ones. 5+10+12+5+8+15 = 55.\n\n### Reliability: Mistral Vibe CLI +26\n\n- Mistral Vibe CLI (69): Local-package reading. PyPI, uv, pip, Homebrew at 3.0.4 and an install script, with Python 3.12 or later stated and UNIX the supported target (20). A public CI workflow on push and pull request to main runs pre-commit, the test suite and a build and install smoke matrix, but GitHub's pages and API were refused in this session, so whether main is passing is unchecked (15 of 25). The 18 October issue counts came from shields.io badges, a third-party copy of GitHub data this run bars, so they are struck. Every release has a Fixed section in the changelog, and how many open issues are crashes or regressions, and how fast they're answered, couldn't be read (10 of 25). The changelog states Keep a Changelog and semver and marks breaking changes, but the hooks rename shipped in minor 2.21.0, patch 2.11.1 changed the `-p` approval default, patch 2.26.1 removed the bundled local model, and patches 3.0.3 and 3.0.4 carry marked config, model and session breaks (9). 3.0.4, classified Production/Stable (15). 20+15+10+9+15 = 69.\n- Verdent (43): Local-package reading, as for the other closed-source harnesses. The desktop app installs from verdent.ai with macOS 11 or later and 64-bit Windows 10 and 11 stated, and the extension from the editor marketplaces, but not from a package registry (15). No public CI or test suite, since the source isn't published (0). No public issue tracker, every task runs through Verdent's servers, and no status page was found, so there is no readable record (5). A dated changelog by version, with the end of Free Mode called out in v2.18.0, but no breaking-change sections (8). 2.18.0, generally available (15). 15+0+5+8+15 = 43.\n\n### Transparency \u0026 trust: Mistral Vibe CLI +26\n\n- Mistral Vibe CLI (81): Apache-2.0, with LICENSE and pyproject in agreement (30). The README sends readers to Mistral's privacy policy (effective 3 September 2026), which names Vibe. The commercial terms (effective 25 September 2026) say no training on customer data unless a product's default or an opt-in allows it, and the pricing page lists model training as opt-out on Free, Pro and Team. The configuration reference calls telemetry anonymous without listing its fields. The offline guide now names `enable_update_checks = false` with `enable_telemetry = false`, as the source reads them (16 of 30; 14 on 18 October, when it named a key the source defines but never reads). Removals are listed in the changelog, deprecated settings are named in the configuration reference and warned about at startup, the agent socket may change without notice, and custom Python tools and the bundled local model were removed in patch releases with warnings (10 of 20). Telemetry is disclosed with an opt-out in the README and the configuration reference, and the README names the server-managed shell-tool rollout, but its fields are only in the source (14 of 20). 30+16+10+14 = 70.\n- Verdent (55): Proprietary, under terms from Verdent AI, Inc. that are clear on use and ownership (15). The privacy policy and security page agree that data stays in the US and that input isn't trained on without consent, and the security page lists subprocessors. The privacy policy gives no retention periods, names MiniMax as a provider the security list leaves out, and deletion is by email request (14). The credit bonus carries a promise of 15 days' notice, but Free Mode was retired on the day v2.18.0 shipped and no deprecation policy was found (6). Subprocessors and their locations are listed, and the domains the app calls are named, with event logging undescribed (12). 15+14+6+12 = 47.\n\n### Security \u0026 auth: Mistral Vibe CLI +25\n\n- Mistral Vibe CLI (58): Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Telemetry and crash reporting are on by default with an opt-out, and the source sends tool names, approval decisions, the model and file counts to api.mistral.ai only when a Mistral key is set. Telemetry also turns on GrowthBook experiments, and one of them (`vibe_cli_smart_approve_default`) can make smart-approve the default. Credentials are Mistral keys in an environment variable, a plaintext `~/.vibe/.env` or the keyring, workspace-scoped with optional expiry per the mistral-api listing, and MCP servers can use OAuth (12 of 30). Five agents with a read-only plan agent and bash allow and deny lists, a prompt for access outside the working directory, `outside_workdir = \"deny\"` (3.0.3) to refuse it outright, an admin `enable_auto_approve = false` (3.0.1) that forbids auto-approve, and `pre_tool` hooks that can deny calls. The default auto-approves file edits, and there's no sandbox on the host (13 of 20; 11 on 18 October, before the two settings). Project config, hooks and MCP servers load only from trusted folders, and `-p` needs `--trust` to load them. The safety page warns that smart-approve isn't a sandbox. No network egress control on the host, and MAI-2026-003 says injected instructions could trigger the bypassed commands (8 of 15). OpenTelemetry tracing is opt-in, with default, strict and no redaction, and each run can write a session journal and an export with the effective config. Managed admin config exists, and audit logs come with the Enterprise plan (13). SECURITY.md asks for private reports, security.txt is valid (expires 5 May 2027) and links a HackerOne form, and Mistral publishes dated advisories with CVEs, three to 2 November. No bounty terms or certification report were read, so 12, as mistral-api and mistral-voxtral-transcribe take on the same Mistral pages (14 on 18 October). 12+13+8+13+12 = 58.\n- Verdent (33): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). Conversation history and tool results go to Verdent's US servers and on to Azure, Bedrock or Vertex, with zero data retention stated for Vertex and Bedrock only. Event logging to log.verdent.ai has no documented opt-out. BYOA keys stay on the machine (10). Plan Mode is read-only, Agent Mode asks before destructive commands and edits outside scope, and workers are isolated by git worktree, but there is no sandbox or network control and the approval list isn't enumerated (9). No prompt-injection guidance found, while web search and fetch results enter the context (2). Usage history in the dashboard, no audit log found (5). A security page with a disclosure address and a five-day acknowledgement, SOC 2 and ISO/IEC 42001 being pursued rather than held, no security.txt and no bug bounty (7). 10+9+2+5+7 = 33.\n\n## Score by category\n\n| Category | Weight | Mistral Vibe CLI | Verdent | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 69 | 43 | Mistral Vibe CLI +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 55 | Mistral Vibe CLI +30 |\n| Agent ergonomics | 13% (16.2 this run) | 84 | 35 | Mistral Vibe CLI +49 |\n| Security \u0026 auth | 14% (17.5 this run) | 58 | 33 | Mistral Vibe CLI +25 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Mistral Vibe CLI +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 73 | 61 | Mistral Vibe CLI +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 81 | 55 | Mistral Vibe CLI +26 |\n| Negative events | ≤15 | -14 | -2 | |\n| **Total** | | **58.4 · C** | **39.7 · E** | |\n\n## Facts side by side\n\n| Fact | Mistral Vibe CLI | Verdent |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Mistral AI | Verdent AI, Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Paid |\n| x402 | no | no |\n| Licence | Apache-2.0 | Proprietary. The terms of use from Verdent AI, Inc. forbid reverse engineering or copying any component, and no source is published |\n| Read-only variant documented | yes | yes |\n| llms.txt | yes | no |\n| Last release | 2026-10-30 | 2026-10-29 |\n| Terms last updated | 2026-09-25 | 2026-05-25 |\n| Privacy policy last updated | 2026-09-03 | 2026-05-26 |\n| Customer content may train models | yes, with an opt-out | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 5.1k stars, 332k PyPI/wk | none |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Mistral Vibe CLI\n\n- -4.6 on 2 November 2026 (B to C): product, correction, negative event\n- +0.1 on 27 October 2026: checklist\n\n### Verdent\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Mistral Vibe CLI.** Apache-2.0 with releases most weeks, and headless runs capped by turns, tokens, price and wall time, with typed exit codes and an export file. File edits are auto-approved by default, the host has no sandbox, telemetry is on by default, and patch releases 3.0.3 and 3.0.4 shipped marked breaking changes.\n\n**Verdent.** A desktop and editor coding agent that splits a goal into parallel workers in git worktrees, with a read-only Plan Mode, MCP servers and the option to run workers on Claude Code or Codex. It has no CLI, API or sandbox, sends context through Verdent's servers, and has had no free tier since 29 October 2026.\n\n## Before you call either\n\n### Mistral Vibe CLI\n\n1. Pass `--agent` on every `-p` run (`plan` is read-only). The default is `accept-edits`, and an experiment can switch it to `smart-approve`\n2. Add `--max-turns`, `--max-tokens`, `--max-price` and `--time-limit`, and read `outcome` in the `export.json` that `--output-dir` writes. Exit 3 means a limit or a refusal\n3. Run in a container or behind `--agent-socket` before using `--auto-approve`, and set `outside_workdir = \"deny\"` to refuse paths outside the working directory\n4. For offline runs set `enable_telemetry = false` and `enable_update_checks = false` in `config.toml`\n5. Pin a version and read the changelog before upgrading, since patch releases can carry marked breaking changes; serve token usage from third-party model servers (`stream_options.include_usage`)\n\n### Verdent\n\n1. Don't plan to drive Verdent headless. Hand the task to the person using the desktop app, or use a harness with a print mode\n2. Start large changes in Plan Mode and review plan.md before switching to Agent Mode\n3. Add MCP servers in the project's .mcp.json or ~/.verdent/mcp.json in the mcpServers shape\n4. Keep work under git, since rollback relies on git and there is no sandbox\n5. Budget in credits at about $0.059 each, because there is no free allowance since 29 October 2026\n\n## Questions\n\n### Which is better for AI agents, Mistral Vibe CLI or Verdent?\n\nMistral Vibe CLI scores 58.4 (C) on agent readiness against Verdent's 39.7 (E), and leads in every scored category.\n\n### Are Mistral Vibe CLI and Verdent open source?\n\nMistral Vibe CLI is open source (Apache-2.0). No open-source release is listed for Verdent.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent.json, and with the fewest tokens: https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"mistral-vibe-cli\", \"b\": \"verdent\"}`. From a terminal: `anchor compare mistral-vibe-cli verdent`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/mistral-vibe-cli.json and https://www.anchorterminal.com/api/v1/tools/verdent.json\n\n## Other comparisons with Mistral Vibe CLI or Verdent\n\n- [Agent Zero vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli.md)\n- [Agent Zero vs Verdent](https://www.anchorterminal.com/compare/agent-zero-vs-verdent.md)\n- [Aider vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/aider-vs-mistral-vibe-cli.md)\n- [Aider vs Verdent](https://www.anchorterminal.com/compare/aider-vs-verdent.md)\n- [Amp vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/amp-vs-mistral-vibe-cli.md)\n- [Amp vs Verdent](https://www.anchorterminal.com/compare/amp-vs-verdent.md)\n- [Antigravity CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-mistral-vibe-cli.md)\n- [Antigravity CLI vs Verdent](https://www.anchorterminal.com/compare/antigravity-cli-vs-verdent.md)\n- [Auggie CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/auggie-vs-mistral-vibe-cli.md)\n- [Auggie CLI vs Verdent](https://www.anchorterminal.com/compare/auggie-vs-verdent.md)\n- [AXLR vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli.md)\n- [AXLR vs Verdent](https://www.anchorterminal.com/compare/axlr-vs-verdent.md)\n- [Claude Code vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/claude-code-vs-mistral-vibe-cli.md)\n- [Claude Code vs Verdent](https://www.anchorterminal.com/compare/claude-code-vs-verdent.md)\n- [Cline vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/cline-vs-mistral-vibe-cli.md)\n- [Cline vs Verdent](https://www.anchorterminal.com/compare/cline-vs-verdent.md)\n- [Conductor vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/conductor-vs-mistral-vibe-cli.md)\n- [Conductor vs Verdent](https://www.anchorterminal.com/compare/conductor-vs-verdent.md)\n- [Crush vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli.md)\n- [Crush vs Verdent](https://www.anchorterminal.com/compare/crush-vs-verdent.md)\n- [Cursor CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-mistral-vibe-cli.md)\n- [Cursor CLI vs Verdent](https://www.anchorterminal.com/compare/cursor-cli-vs-verdent.md)\n- [DeepSeek Harness (dsh) vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-mistral-vibe-cli.md)\n- [DeepSeek Harness (dsh) vs Verdent](https://www.anchorterminal.com/compare/deepseek-harness-vs-verdent.md)\n- [dsh-superagent (DeepSeek) vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-mistral-vibe-cli.md)\n- [dsh-superagent (DeepSeek) vs Verdent](https://www.anchorterminal.com/compare/deepseek-superagent-vs-verdent.md)\n- [Devin vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/devin-vs-mistral-vibe-cli.md)\n- [Devin vs Verdent](https://www.anchorterminal.com/compare/devin-vs-verdent.md)\n- [Droid CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/droid-cli-vs-mistral-vibe-cli.md)\n- [Droid CLI vs Verdent](https://www.anchorterminal.com/compare/droid-cli-vs-verdent.md)\n- [Pi vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli.md)\n- [Pi vs Verdent](https://www.anchorterminal.com/compare/earendil-pi-vs-verdent.md)\n- [Emdash vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli.md)\n- [Emdash vs Verdent](https://www.anchorterminal.com/compare/emdash-vs-verdent.md)\n- [Gemini CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli.md)\n- [Gemini CLI vs Verdent](https://www.anchorterminal.com/compare/gemini-cli-vs-verdent.md)\n- [GitHub Copilot CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/github-copilot-cli-vs-mistral-vibe-cli.md)\n- [GitHub Copilot CLI vs Verdent](https://www.anchorterminal.com/compare/github-copilot-cli-vs-verdent.md)\n- [goose vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/goose-vs-mistral-vibe-cli.md)\n- [goose vs Verdent](https://www.anchorterminal.com/compare/goose-vs-verdent.md)\n- [Harness² vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.md)\n- [Harness² vs Verdent](https://www.anchorterminal.com/compare/harness2-vs-verdent.md)\n- [HarnessRouter vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli.md)\n- [HarnessRouter vs Verdent](https://www.anchorterminal.com/compare/harnessrouter-vs-verdent.md)\n- [Jules vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli.md)\n- [Jules vs Verdent](https://www.anchorterminal.com/compare/jules-vs-verdent.md)\n- [Junie CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/junie-vs-mistral-vibe-cli.md)\n- [Junie CLI vs Verdent](https://www.anchorterminal.com/compare/junie-vs-verdent.md)\n- [Kilo Code CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/kilo-code-cli-vs-mistral-vibe-cli.md)\n- [Kilo Code CLI vs Verdent](https://www.anchorterminal.com/compare/kilo-code-cli-vs-verdent.md)\n- [Kimi Code CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/kimi-code-cli-vs-mistral-vibe-cli.md)\n- [Kimi Code CLI vs Verdent](https://www.anchorterminal.com/compare/kimi-code-cli-vs-verdent.md)\n- [Kiro CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/kiro-cli-vs-mistral-vibe-cli.md)\n- [Kiro CLI vs Verdent](https://www.anchorterminal.com/compare/kiro-cli-vs-verdent.md)\n- [Letta vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/letta-vs-mistral-vibe-cli.md)\n- [Letta vs Verdent](https://www.anchorterminal.com/compare/letta-vs-verdent.md)\n- [mini-swe-agent vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/mini-swe-agent-vs-mistral-vibe-cli.md)\n- [mini-swe-agent vs Verdent](https://www.anchorterminal.com/compare/mini-swe-agent-vs-verdent.md)\n- [MiniMax Code vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/minimax-code-vs-mistral-vibe-cli.md)\n- [MiniMax Code vs Verdent](https://www.anchorterminal.com/compare/minimax-code-vs-verdent.md)\n- [Mistral Vibe CLI vs Muse Code](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-muse-code.md)\n- [Mistral Vibe CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api.md)\n- [Mistral Vibe CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-codex.md)\n- [Mistral Vibe CLI vs OpenCode](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-opencode.md)\n- [Mistral Vibe CLI vs OpenHands](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openhands.md)\n- [Mistral Vibe CLI vs OpenMausBot](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openmausbot.md)\n- [Mistral Vibe CLI vs Orca](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca.md)\n- [Mistral Vibe CLI vs Paseo](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paseo.md)\n- [Mistral Vibe CLI vs Prime Agent](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-prime-agent.md)\n- [Mistral Vibe CLI vs Qoder CLI](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qoder-cli.md)\n- [Mistral Vibe CLI vs Qwen Code](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-qwen-code.md)\n- [Mistral Vibe CLI vs Mirror CLI](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-reflection-mirror.md)\n- [Mistral Vibe CLI vs Rovo Dev CLI](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-rovo-dev-cli.md)\n- [Mistral Vibe CLI vs Sculptor](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor.md)\n- [Mistral Vibe CLI vs T3 Code](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code.md)\n- [Mistral Vibe CLI vs Traycer](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-traycer.md)\n- [Mistral Vibe CLI vs Unstoppable](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-unstoppable.md)\n- [Mistral Vibe CLI vs Vibe-Trading](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-vibe-trading.md)\n- [Mistral Vibe CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp.md)\n- [Muse Code vs Verdent](https://www.anchorterminal.com/compare/muse-code-vs-verdent.md)\n- [OpenAI Agents API vs Verdent](https://www.anchorterminal.com/compare/openai-agents-api-vs-verdent.md)\n- [OpenAI Codex vs Verdent](https://www.anchorterminal.com/compare/openai-codex-vs-verdent.md)\n- [OpenCode vs Verdent](https://www.anchorterminal.com/compare/opencode-vs-verdent.md)\n- [OpenHands vs Verdent](https://www.anchorterminal.com/compare/openhands-vs-verdent.md)\n- [Orca vs Verdent](https://www.anchorterminal.com/compare/orca-vs-verdent.md)\n- [Paseo vs Verdent](https://www.anchorterminal.com/compare/paseo-vs-verdent.md)\n- [Prime Agent vs Verdent](https://www.anchorterminal.com/compare/prime-agent-vs-verdent.md)\n- [Qoder CLI vs Verdent](https://www.anchorterminal.com/compare/qoder-cli-vs-verdent.md)\n- [Qwen Code vs Verdent](https://www.anchorterminal.com/compare/qwen-code-vs-verdent.md)\n- [Mirror CLI vs Verdent](https://www.anchorterminal.com/compare/reflection-mirror-vs-verdent.md)\n- [Rovo Dev CLI vs Verdent](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-verdent.md)\n- [Sculptor vs Verdent](https://www.anchorterminal.com/compare/sculptor-vs-verdent.md)\n- [T3 Code vs Verdent](https://www.anchorterminal.com/compare/t3-code-vs-verdent.md)\n- [Traycer vs Verdent](https://www.anchorterminal.com/compare/traycer-vs-verdent.md)\n- [Verdent vs Vibe-Trading](https://www.anchorterminal.com/compare/verdent-vs-vibe-trading.md)\n- [Verdent vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/verdent-vs-warp.md)\n- [Clawboo vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/clawboo-vs-mistral-vibe-cli.md)\n- [Clawboo vs Verdent](https://www.anchorterminal.com/compare/clawboo-vs-verdent.md)\n- [CLI Manager vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/cli-manager-vs-mistral-vibe-cli.md)\n- [CLI Manager vs Verdent](https://www.anchorterminal.com/compare/cli-manager-vs-verdent.md)\n- [Harness vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-mistral-vibe-cli.md)\n- [Harness vs Verdent](https://www.anchorterminal.com/compare/harness-autonomous-vs-verdent.md)\n- [Mistral Vibe CLI vs Paperclip](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-paperclip.md)\n- [Mistral Vibe CLI vs Parallax](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-parallax-agents.md)\n- [OpenMausBot vs Verdent](https://www.anchorterminal.com/compare/openmausbot-vs-verdent.md)\n- [Paperclip vs Verdent](https://www.anchorterminal.com/compare/paperclip-vs-verdent.md)\n- [Parallax vs Verdent](https://www.anchorterminal.com/compare/parallax-agents-vs-verdent.md)\n- [Unstoppable vs Verdent](https://www.anchorterminal.com/compare/unstoppable-vs-verdent.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Mistral Vibe CLI vs Verdent", "url": "" } ], "description": "Mistral Vibe CLI scores 58.4 (C) to Verdent's 39.7 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Mistral Vibe CLI C 58.4", "Verdent E 39.7", "scores" ], "h1": "Mistral Vibe CLI vs Verdent", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/mistral-vibe-cli-vs-verdent", "published": "2026-10-01", "section": "tools", "title": "Mistral Vibe CLI vs Verdent for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-verdent" }, "tokens": { "markdown": 7350, "slim": 3430 }, "version": 1 }