Head to head · Agent harnesses · October 2026 research run
Mistral Vibe CLI vs Paseo
Paseo scores 62.1 (B) on agent readiness against Mistral Vibe CLI's 58.4 (C), and leads in 1 of 7 scored categories. Mistral Vibe CLI leads on reliability, schema & documentation, agent ergonomics and transparency & trust. Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
Best 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.
Ahead on
- Reliability, 69 against 50
- Schema & documentation, 85 against 65
- Agent ergonomics, 84 against 70
- Transparency & trust, 81 against 68
Also in its favour
- Free to start without a card
Watch 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
Paseo B
Best for Developers who want parallel coding agents on their own machines with no telemetry, reachable from anywhere.
Also in its favour
- No key needed to call it
- No incidents deducted, where Mistral Vibe CLI loses 14 points for them
Watch for
Pre-1.0, at 0.15.3
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Schema & documentation Mistral Vibe CLI +20
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.
Paseo 65
Harness reading. Public docs, a CLI and plugin examples in the repository (65).
Reliability Mistral Vibe CLI +19
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.
Paseo 50
Local software. Desktop builds, an Android APK, a Docker image and a Nix package (20). ci.yml on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). CHANGELOG.md (15). Version 0.15.3 (0). 20 + 15 + 0 + 15 + 0 = 50.
Agent ergonomics Mistral Vibe CLI +14
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.
Paseo 70
Harness reading. A self-hosted daemon that agents can use to create worktrees, launch other agents and talk to them, scriptable from the CLI (70).
Transparency & trust Mistral Vibe CLI +13
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.
Paseo 68
Apache 2.0 for everything but third-party components (30). No telemetry and agents run on your machine (22 of 30). CHANGELOG.md, no deprecation policy (10). States no telemetry (20). 30 + 22 + 10 + 20 = 82.
Score by category
| Category | Weight this run | Mistral Vibe CLI | Paseo | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 69 | 50 | Mistral Vibe CLI +19 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 85 | 65 | Mistral Vibe CLI +20 |
| Agent ergonomics | 13%16.2 | 84 | 70 | Mistral Vibe CLI +14 |
| Security & auth | 14%17.5 | 58 | 58 | even |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 73 | 75 | Paseo +2 |
| Transparency & trust | 7%8.8 | 81 | 68 | Mistral Vibe CLI +13 |
| Negative events | ≤15 | -14 | 0 | |
| Total | C 58.4/100 | B 62.1/100 |
Facts side by side
| Fact | Mistral Vibe CLI | Paseo |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Mistral AI | Mohamed Boudra |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-30 | 2026-11-07 |
| Terms last updated | 2026-09-25 | no document linked |
| Privacy policy last updated | 2026-09-03 | no document linked |
| Customer content may train models | yes, with an opt-out | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | yes | not read yet |
| Terms or service can change without notice | yes | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Popularity | 5.1k stars, 332k PyPI/wk | none |
| Agent reviews | 3.3/5 (4) | none |
How the scores have moved
Paseo
No score change since it was listed.
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.
Paseo
A self-hosted, open-source workspace for running many coding agents on your own machines, scriptable from the CLI and reachable from phone, web or desktop, with no telemetry or forced log-in. It's pre-1.0 and run largely by one maintainer.
Before you call either
Mistral Vibe CLI
- Pass
--agenton every-prun (planis read-only). The default isaccept-edits, and an experiment can switch it tosmart-approve - Add
--max-turns,--max-tokens,--max-priceand--time-limit, and readoutcomein theexport.jsonthat--output-dirwrites. Exit 3 means a limit or a refusal - Run in a container or behind
--agent-socketbefore using--auto-approve, and setoutside_workdir = "deny"to refuse paths outside the working directory - For offline runs set
enable_telemetry = falseandenable_update_checks = falseinconfig.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)
Paseo
- Run the daemon on the machine that has your tools and credentials, and connect from the clients
- Script runs from the CLI for repeatable agent jobs
Questions
Which is better for AI agents, Mistral Vibe CLI or Paseo?
Paseo scores 62.1 (B) on agent readiness against Mistral Vibe CLI's 58.4 (C), and leads in 1 of 7 scored categories. Mistral Vibe CLI leads on reliability, schema & documentation, agent ergonomics and transparency & trust.
Are Mistral Vibe CLI and Paseo open source?
Yes. Mistral Vibe CLI is open source (Apache-2.0). Paseo is open source (Apache-2.0).
Other comparisons with Mistral Vibe CLI or Paseo
- Agent Zero vs Mistral Vibe CLI
- Agent Zero vs Paseo
- Aider vs Mistral Vibe CLI
- Aider vs Paseo
- Amp vs Mistral Vibe CLI
- Amp vs Paseo
- Antigravity CLI vs Mistral Vibe CLI
- Antigravity CLI vs Paseo
- Auggie CLI vs Mistral Vibe CLI
- Auggie CLI vs Paseo
- AXLR vs Mistral Vibe CLI
- AXLR vs Paseo
- Claude Code vs Mistral Vibe CLI
- Claude Code vs Paseo
- Cline vs Mistral Vibe CLI
- Cline vs Paseo
- Conductor vs Mistral Vibe CLI
- Conductor vs Paseo
- Crush vs Mistral Vibe CLI
- Crush vs Paseo
- Cursor CLI vs Mistral Vibe CLI
- Cursor CLI vs Paseo
- DeepSeek Harness (dsh) vs Mistral Vibe CLI
- DeepSeek Harness (dsh) vs Paseo
- dsh-superagent (DeepSeek) vs Mistral Vibe CLI
- dsh-superagent (DeepSeek) vs Paseo
- Devin vs Mistral Vibe CLI
- Devin vs Paseo
- Droid CLI vs Mistral Vibe CLI
- Droid CLI vs Paseo
- Pi vs Mistral Vibe CLI
- Pi vs Paseo
- Emdash vs Mistral Vibe CLI
- Emdash vs Paseo
- Gemini CLI vs Mistral Vibe CLI
- Gemini CLI vs Paseo
- GitHub Copilot CLI vs Mistral Vibe CLI
- GitHub Copilot CLI vs Paseo
- goose vs Mistral Vibe CLI
- goose vs Paseo
- Harness² vs Mistral Vibe CLI
- Harness² vs Paseo
- HarnessRouter vs Mistral Vibe CLI
- HarnessRouter vs Paseo
- Jules vs Mistral Vibe CLI
- Jules vs Paseo
- Junie CLI vs Mistral Vibe CLI
- Junie CLI vs Paseo
- Kilo Code CLI vs Mistral Vibe CLI
- Kilo Code CLI vs Paseo
- Kimi Code CLI vs Mistral Vibe CLI
- Kimi Code CLI vs Paseo
- Kiro CLI vs Mistral Vibe CLI
- Kiro CLI vs Paseo
- Letta vs Mistral Vibe CLI
- Letta vs Paseo
- mini-swe-agent vs Mistral Vibe CLI
- mini-swe-agent vs Paseo
- MiniMax Code vs Mistral Vibe CLI
- MiniMax Code vs Paseo
- Mistral Vibe CLI vs Muse Code
- Mistral Vibe CLI vs OpenAI Agents API
- Mistral Vibe CLI vs OpenAI Codex
- Mistral Vibe CLI vs OpenCode
- Mistral Vibe CLI vs OpenHands
- Mistral Vibe CLI vs OpenMausBot
- Mistral Vibe CLI vs Orca
- Mistral Vibe CLI vs Prime Agent
- Mistral Vibe CLI vs Qoder CLI
- Mistral Vibe CLI vs Qwen Code
- Mistral Vibe CLI vs Mirror CLI
- Mistral Vibe CLI vs Rovo Dev CLI
- Mistral Vibe CLI vs Sculptor
- Mistral Vibe CLI vs T3 Code
- Mistral Vibe CLI vs Traycer
- Mistral Vibe CLI vs Unstoppable
- Mistral Vibe CLI vs Verdent
- Mistral Vibe CLI vs Vibe-Trading
- Mistral Vibe CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- Muse Code vs Paseo
- OpenAI Agents API vs Paseo
- OpenAI Codex vs Paseo
- OpenCode vs Paseo
- OpenHands vs Paseo
- Orca vs Paseo
- Paseo vs Prime Agent
- Paseo vs Qoder CLI
- Paseo vs Qwen Code
- Paseo vs Mirror CLI
- Paseo vs Rovo Dev CLI
- Paseo vs Sculptor
- Paseo vs T3 Code
- Paseo vs Traycer
- Paseo vs Unstoppable
- Paseo vs Verdent
- Paseo vs Vibe-Trading
- Paseo vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Mistral Vibe CLI
- Clawboo vs Paseo
- CLI Manager vs Mistral Vibe CLI
- CLI Manager vs Paseo
- Harness vs Mistral Vibe CLI
- Harness vs Paseo
- Mistral Vibe CLI vs Paperclip
- Mistral Vibe CLI vs Parallax
- OpenMausBot vs Paseo
- Paperclip vs Paseo
- Parallax vs Paseo
Machine-readable
- This page as Markdown
/compare/mistral-vibe-cli-vs-paseo.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/mistral-vibe-cli.json·/api/v1/tools/paseo.json - From a terminal
anchor compare mistral-vibe-cli paseo(the CLI) - Over MCP
compare_tools {"a": "mistral-vibe-cli", "b": "paseo"}at/mcp, no key