{ "data": { "a": { "slug": "crush", "name": "Crush", "vendor": "Charm", "vendorUrl": "https://charm.land", "kind": "harness", "category": "agent-harnesses", "summary": "Terminal coding agent from Charm, written in Go, that works with the model of the owner's choice. It has a TUI, a one-shot `crush run` mode, LSP context, MCP servers, Agent Skills and an optional local client-server mode.", "url": "https://www.anchorterminal.com/tools/crush", "markdownUrl": "https://www.anchorterminal.com/tools/crush.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/crush.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/crush.json", "dns": "crush.grade.anchorterminal.com", "repo": "https://github.com/charmbracelet/crush", "license": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)", "transports": [], "packages": [ { "registry": "npm", "name": "@charmland/crush" }, { "registry": "go", "name": "github.com/charmbracelet/crush" } ], "auth": "mixed", "authNotes": "No Charm account is needed. Provider keys come from environment variables such as `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`, the model picker or a `crushrc`, local models need none, and Charm's Hyper provider uses a device login. `crush server` has no authentication and listens on a per-user Unix socket by default.", "pricing": "freemium", "pricingNotes": "The CLI is free to use under FSL-1.1-MIT. You pay your model provider, or Charm's Hyper subscription, which the README says has a free tier. Hyper's public provider file lists per-million-token figures for 22 models. Plan prices sit in a script-rendered app and weren't read.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs folder or the source (checked 2026-10-18).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 29000, "npmWeekly": 5594, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://github.com/charmbracelet/crush#readme", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "harness", "coding-agent", "cli", "source-available", "go", "mcp", "telemetry-default-on", "pre-1.0", "freemium", "no-card", "local" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 49.8, "grade": "D", "agentReady": false, "rank": 973, "ranked": true, "rankOf": 1354, "categoryRank": 34, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 52, "maintenance": 82, "payments": 55, "reliability": 52, "schema": 65, "security": 41, "transparency": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -6, "negativeNotes": [ "23 October 2026. Released fix of a described flaw with no advisory found. v0.98.2 carried 1dbd303a, which says write, edit and multiedit created parent directories before the permission prompt, so \"An agent could mkdir -p anywhere on the machine with no consent\". OSV lists no advisory for Crush, so 3 is deducted (https://github.com/charmbracelet/crush/commit/1dbd303a).", "30 October 2026. Fix in no release. fd40067e, merged to main on 30 October and carried only by the `nightly` pre-release, says an \"allow for this session\" approval of one shell command \"stood in for every command run in that directory afterwards, however dangerous, with no further prompt\". v0.99.0 (29 October) still keys session grants on tool, action and path. 3 is deducted until a release carries it (https://github.com/charmbracelet/crush/commit/fd40067e)." ], "verdict": "Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.", "bestFor": "Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.", "strengths": [ "Any OpenAI- or Anthropic-compatible provider, Bedrock, Vertex, Azure and local models through Ollama, llama.cpp, LM Studio or LiteLLM, with no Charm account", "PreToolUse hooks, compatible with Claude Code's format, can block or rewrite tool calls", "Releases cosign-signed, with CodeQL, Grype and govulncheck in CI", "19 releases from 7 August to 29 October 2026, the latest v0.99.0 on 29 October", "Built for macOS, Linux, Windows, Android and three BSDs, with packages for npm, Homebrew, Winget, Scoop, apt, yum and Nix" ], "weaknesses": [ "`crush run` approves every permission request automatically, which the README doesn't mention", "No sandbox, only a refusal list of shell commands, and permission fixes merged on 30 October 2026 are in no release yet", "A project's `.crushrc` and `$(...)` in `crush.json` run as code when Crush starts", "Usage metrics are on by default and are linked to the Hyper account after a Hyper login", "No JSON output, turn limit or cost limit for `crush run`, and the client-server API is opt-in and has no authentication" ], "agentNotes": [ "Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session, and a session approval in v0.99.0 covers later commands in the same directory", "Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup", "Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land", "Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag", "Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.8 } ], "editorialScores": { "ergonomics": 52, "maintenance": 82, "payments": 55, "reliability": 52, "schema": 65, "security": 41, "transparency": 49 }, "provenanceScore": 69, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @charmland/crush # or: brew install charmbracelet/tap/crush", "headless": { "command": "crush run --quiet \"$TASK\"", "env": { "CRUSH_DISABLE_METRICS": "1" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/crush" }, "area": "frameworks", "unitPrices": [ { "item": "Hyper, qwen3.8-max (default large model), input", "unit": "1m-tokens", "usd": 2, "note": "output $6, from Hyper's public provider file" }, { "item": "Hyper, deepseek-v4.1-flash (default small model), input", "unit": "1m-tokens", "usd": 0.33, "note": "output $1.31, from Hyper's public provider file" } ], "provenance": { "legalEntity": "Charmbracelet, Inc.", "domain": "charm.land", "domainRegistered": "2023-08-17", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/charmbracelet/crush/releases", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "LICENSE.md and the charm.land footer name Charmbracelet, Inc.", "charm.land/privacy, charm.land/terms and charm.land/.well-known/security.txt return Charm's not-found page. Hyper links Terms of Service and a Privacy Policy at hyper.charm.land/legal, which render by script and weren't read.", "The organisation's SECURITY.md gives vt100@charm.sh for reports. The crush repository has no SECURITY.md of its own.", "Release notes are generated from commit messages on GitHub releases. There is no CHANGELOG file in the repository." ], "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/crush.json", "live": { "slug": "crush", "versions": [ { "registry": "github", "name": "charmbracelet/crush", "version": "v0.100.0", "released": "2026-11-05", "seenAt": "2026-11-05T21:24:11.574320552Z" }, { "registry": "npm", "name": "@charmland/crush", "version": "0.100.0", "seenAt": "2026-11-05T21:24:10.776183954Z" } ], "githubStars": 28968, "npmWeekly": 19494, "securityTxt": { "url": "https://charm.land/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:55:36.770438073Z" }, "domain": { "domain": "charm.land", "registered": "2023-08-17", "source": "https://rdap.identitydigital.services/rdap/domain/charm.land", "checkedAt": "2026-11-01T14:21:15.41389399Z" }, "github": { "repo": "charmbracelet/crush", "checkedAt": "2026-11-02T08:37:55.400043602Z", "stars": 28910, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T07:41:22Z", "openIssues": 284, "openPRs": 244, "issuesOpened90d": 174, "issuesClosed90d": 262, "prsMerged90d": 203, "ci": { "branch": "main", "runs": 50, "success": 46, "failure": 1, "other": 3, "latest": "success", "latestAt": "2026-11-02T07:43:21Z" }, "replies": { "sampled": 25, "unanswered": 17, "medianDays": 4.9 } }, "updatedAt": "2026-11-05T21:24:11.574320552Z" } }, "answer": "OpenAI Agents API scores 73.3 (BB) on agent readiness against Crush's 49.8 (D), and leads in 6 of 7 scored categories. Crush leads on payments \u0026 pricing.", "b": { "slug": "openai-agents-api", "name": "OpenAI Agents API", "vendor": "OpenAI", "vendorUrl": "https://openai.com/index/introducing-the-agents-api/", "kind": "http-api", "category": "agent-harnesses", "summary": "The OpenAI Agents API runs OpenAI's managed Codex harness as a hosted service. One call creates a session with a model, tools, MCP servers, subagents and an OpenAI-hosted or self-hosted sandbox, and OpenAI runs the loop.", "url": "https://www.anchorterminal.com/tools/openai-agents-api", "markdownUrl": "https://www.anchorterminal.com/tools/openai-agents-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openai-agents-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json", "dns": "openai-agents-api.grade.anchorterminal.com", "license": "Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0", "transports": [ "https" ], "remoteUrl": "https://api.openai.com/v1/agents/sessions", "packages": [ { "registry": "pypi", "name": "openai" }, { "registry": "npm", "name": "openai" } ], "auth": "api-key", "authNotes": "An OpenAI project API key as a Bearer token, with the header `OpenAI-Beta: agents=v1`. Project keys can be restricted per endpoint or read-only, and service accounts and workload identity federation are available, per the openai-api listing. Signing up and creating a key need a person in a browser.", "pricing": "usage", "pricingNotes": "No fee for the API itself. Model tokens are billed at the chosen model's API rates, OpenAI tools at their built-in rates (web search $10.00 per 1,000 calls plus content tokens), and OpenAI-hosted sandboxes at container rates, $0.03 for 1 GB, $0.12 for 4 GB, $0.48 for 16 GB and $1.92 for 64 GB per 20-minute session, billed by the minute with a 5-minute minimum. Since 9 October sandbox compute is billed only during active turns (checked 2026-11-06).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Agents API guides or on OpenAI's pricing page; billing is to an OpenAI account (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://developers.openai.com/api/docs/guides/agents-api/overview", "llmsTxt": "https://developers.openai.com/api/docs/llms.txt", "capabilities": [ "agent.harness" ], "tags": [ "official", "hosted", "beta", "usage-priced", "llms-txt", "status-page", "mcp-client", "sandbox", "subagents", "webhooks", "soc2", "iso27001", "bug-bounty" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 73.3, "grade": "BB", "agentReady": true, "rank": 99, "ranked": true, "rankOf": 1354, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 87, "payments": 30, "reliability": 60, "schema": 88, "security": 87, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only.", "bestFor": "Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.", "strengths": [ "One session call configures the model, tools, MCP servers, subagents and the sandbox, and OpenAI runs and recovers the loop", "Sandboxes on OpenAI or self-hosted, with guides for ten providers including E2B, Daytona, Modal, Cloudflare and Vercel", "An errors guide with codes per status and turn, Retry-After and a check-before-retry procedure", "Webhooks, streamed events, tracing and usage views for each session", "SDK examples in Python, JavaScript, Go, Java and Ruby", "Status page with its own Agents component" ], "weaknesses": [ "Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date", "Not eligible for Zero Data Retention, and data residency is United States only", "No idempotency key for session or turn requests; retries depend on checking state first", "One API-wide major outage on 29 September included it, plus several smaller incidents since release", "No retention period stated for published artifacts after a sandbox expires" ], "agentNotes": [ "POST https://api.openai.com/v1/agents/sessions with a project key and the header OpenAI-Beta: agents=v1, or use client.beta.agents in the SDKs", "Before retrying, retrieve the session and turn and check which actions completed, since there's no idempotency key", "Set the sandbox network to restricted with an allowlist of up to 100 hosts when the agent doesn't need the open web", "Save files from /workspace/outputs before deleting a session; no retention period is stated for artifacts", "Don't send data that needs Zero Data Retention or non-US residency; the Agents API supports neither" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73.3 } ], "editorialScores": { "ergonomics": 80, "maintenance": 87, "payments": 30, "reliability": 60, "schema": 88, "security": 87, "transparency": 75 }, "provenanceScore": 95, "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": { "http": "curl https://api.openai.com/v1/agents/sessions \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"OpenAI-Beta: agents=v1\" \\\n -H \"Content-Type: application/json\" \\\n -d @session.json # model, tools, environment and input, per the quickstart" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/openai-agents-api" }, "sameCompany": [ "openai-api", "openai-embeddings", "openai-guardrails", "openai-moderation", "openai-image-api", "openai-sora", "openai-speech-to-text", "gpt-live", "openai-realtime", "openai-agents-sdk", "openai-decisions-api", "openai-codex", "gpt-oss-120b", "gpt-oss-20b" ], "area": "frameworks", "provenance": { "legalEntity": "OpenAI OpCo, LLC", "domain": "openai.com", "domainRegistered": "2007-01-19", "domainNote": "openai.com was registered in 2007, before OpenAI existed, per the openai-api listing.", "endpointOnVendorDomain": true, "terms": "https://openai.com/policies/services-agreement/", "privacy": "https://openai.com/policies/privacy-policy/", "statusPage": "https://status.openai.com", "changelog": "https://developers.openai.com/api/docs/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The endpoint is on api.openai.com, the same host as the rest of the OpenAI API. Terms, privacy, security.txt and the domain are the openai-api listing's readings." ], "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/openai-agents-api.json", "live": { "slug": "openai-agents-api", "probe": { "target": "https://api.openai.com/v1/agents/sessions", "method": "get", "lastAt": "2026-11-06T09:47:41.371658489Z", "lastOk": true, "lastStatus": 400, "lastMs": 162, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 148, "p95ms24h": 166, "samples24h": 47, "samples30d": 47, "days": [ { "date": "2026-11-06", "probes": 47, "ok": 47 } ] }, "vendorStatus": { "page": "https://status.openai.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:43:26.425829944Z" }, "updatedAt": "2026-11-06T09:47:41.371658489Z" } }, "edges": [ { "by": 46, "category": "security", "leads": "openai-agents-api", "name": "Security \u0026 auth", "reasons": { "a": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names two opt-outs (`CRUSH_DISABLE_METRICS=1` and `DO_NOT_TRACK=1`). The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, `permissions deny` hides tools and PreToolUse hooks can block calls. But `crush run` approves every permission request in its session automatically (internal/app/app.go in v0.99.0), `--yolo` skips all prompts, and there's no sandbox, only a refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's `.crushrc` and `$(...)` in `crush.json` run as code at startup, which the README warns about (3). Logs in `./.crush/logs/crush.log` with `crush logs`, sessions in a local database readable as JSON, and `crush stats`, with no OpenTelemetry export (9). The organisation's SECURITY.md is a disclosure policy with a reporting address (vt100@charm.sh) and no response time. CI runs CodeQL, Grype and govulncheck nightly and releases are cosign-signed. OSV lists no advisory for the npm package or the Go module. No security.txt and no bug bounty. A disclosure route with no stated time is this run's 7 (was 10). 15 + 7 + 3 + 9 + 7 = 41.", "b": "Project keys with restricted per-endpoint permissions, service accounts and workload identity, per the openai-api listing; we didn't confirm a key can be limited to /v1/agents (27 of 30). Automatic review for approvals, a sandbox network restricted to a host allowlist, vaults for secrets and a sandbox security guide (17 of 20). The agent reads web pages, MCP results and browser content; the sandbox security guide and approval flow are the mitigations, with no prompt-injection guide of its own found (8 of 15). Tracing, observability and usage per session and admin audit logs (15). SOC 2 Type 2, ISO 27001 family, Bugcrowd bounty and a disclosure policy, per the openai-api listing (20). Not ZDR-eligible and US residency only, recorded under transparency. 27 + 17 + 8 + 15 + 20 = 87." }, "scores": { "a": 41, "b": 87 } }, { "by": 28, "category": "ergonomics", "leads": "openai-agents-api", "name": "Agent ergonomics", "reasons": { "a": "Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8).", "b": "Read as an API an agent drives. Context is compacted automatically, and session budgets and streamed events keep output sized (20 of 25). Sessions can be listed, continued and steered, events streamed or sent by webhook, artifacts fetched (15 of 20). Actionable error codes with recovery steps (20). No idempotency key; a documented check-then-retry procedure (10 of 20). One session call with defaults (medium sandbox, network enabled), SDKs in five languages (15). 20 + 15 + 20 + 10 + 15 = 80." }, "scores": { "a": 52, "b": 80 } }, { "by": 26, "category": "transparency", "leads": "openai-agents-api", "name": "Transparency \u0026 trust", "reasons": { "a": "FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives two opt-outs, but doesn't mention the alias to the Hyper account (15).", "b": "Closed service with clear terms, Apache-2.0 SDKs (15). Session state retained until deleted, deletable sessions and artifacts, not ZDR-eligible, US residency only, and the data-controls guide agrees; no retention period for artifacts after a sandbox expires (25 of 30). Dated deprecation notices with minimum periods for GA models; a beta API can change faster (15 of 20). Subprocessors and processing countries listed, per the openai-api listing (20). 15 + 25 + 15 + 20 = 75." }, "scores": { "a": 59, "b": 85 } }, { "by": 25, "category": "payments", "leads": "crush", "name": "Payments \u0026 pricing", "reasons": { "a": "No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20).", "b": "No machine payment protocol (0). Model, tool and container prices published without a login, and no fee for the API itself (20). The Free tier reading of the openai-api listing, half (10). Sign-up in a browser (0). 0 + 20 + 10 + 0 = 30." }, "scores": { "a": 55, "b": 30 } }, { "by": 23, "category": "schema", "leads": "openai-agents-api", "name": "Schema \u0026 documentation", "reasons": { "a": "Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).", "b": "The reference is linked from the overview and the SDKs carry beta.agents types; we didn't confirm /agents/sessions in OpenAI's public OpenAPI file, so 15 of 25. llms.txt with every Agents API page and Markdown twins (10). The overview, architecture page and the agents guide that compares the Agents API, Agents SDK and Responses API say when to use it (20). Typed configuration with enumerated container sizes, network modes and environment types (13 of 15). Examples in six languages and an errors page with codes per HTTP status, turn and session (15). Dated changelog entries and a versioned beta header (15). 15 + 10 + 20 + 13 + 15 + 15 = 88." }, "scores": { "a": 65, "b": 88 } }, { "by": 8, "category": "reliability", "leads": "openai-agents-api", "name": "Reliability", "reasons": { "a": "Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). The public build workflow runs `go test -race -failfast ./...` on Linux, macOS and Windows for every push to main and every pull request, but GitHub pages and the API answer 403 to us, so results are unread (15). The 18 October issue and pull request counts came from shields.io badges, a third-party copy of GitHub data, and are struck. The repository's own refs show 2,574 pull requests to #4224, 272 of them open with a merge ref, and 147 merges into main in the 90 days to 4 November. Crash and regression issues couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of `crushrc` while still loading (7, held partial). v0.99.0, before 1.0, with no stability statement (0). 20 + 15 + 10 + 7 + 0 = 52.", "b": "Read as a hosted API. status.openai.com has an Agents component under APIs (20). Since release on 10 September (57 days, not 90), the feed names the Agents API in a degraded-performance incident on 14 September, the elevated errors across ChatGPT, Codex and the API on 29 September (the openai-api listing reads that one as a major, 17:52 to 23:14 UTC), computer use issues and degraded workspace agents on 6 and 7 October, degraded performance across the APIs for 22 minutes on 21 October, and overbilling for hosted containers on 19 September. One major, the rest minor (10). Rate limits come from the shared guide, published per tier and model with headers, and the errors page adds a Files API allowance on session creation (15). 429 and 503 guidance with Retry-After, capped backoff and a check-then-retry procedure for turns (15). The Scale Tier SLA in the openai-api listing isn't shown to cover a beta API (0). Public beta behind the agents=v1 header (0). 20 + 10 + 15 + 15 + 0 + 0 = 60." }, "scores": { "a": 52, "b": 60 } } ], "facts": [ { "a": "Agent harness", "b": "HTTP API", "name": "Kind" }, { "a": "Charm", "b": "OpenAI", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.openai.com/v1/agents/sessions", "name": "Hosted endpoint" }, { "a": "", "b": "https", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)", "b": "Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-29", "b": "2026-10-16", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "not read yet", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "29k stars, 5.6k npm/wk", "b": "none", "name": "Popularity" }, { "a": "2.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "OpenAI Agents API scores 73.3 (BB) on agent readiness against Crush's 49.8 (D), and leads in 6 of 7 scored categories. Crush leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Crush or OpenAI Agents API?" }, { "answer": "No hosted endpoint is listed for Crush. OpenAI Agents API has a hosted endpoint at https://api.openai.com/v1/agents/sessions.", "question": "Can an agent call Crush and OpenAI Agents API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 55 against 30" ], "also": [ "Free to start without a card" ], "goodFor": "Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.", "slug": "crush", "watchFor": "`crush run` approves every permission request automatically, which the README doesn't mention" }, { "aheadOn": [ "Reliability, 60 against 52", "Schema \u0026 documentation, 88 against 65", "Agent ergonomics, 80 against 52", "Security \u0026 auth, 87 against 41", "Maintenance \u0026 community, 87 against 82", "Transparency \u0026 trust, 85 against 59" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "No incidents deducted, where Crush loses 6 points for them" ], "goodFor": "Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.", "slug": "openai-agents-api", "watchFor": "Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date" } ], "history": { "crush": [ { "causes": [ "security", "correction" ], "date": "2026-11-04", "delta": -6.9, "from": 56.7, "fromGrade": "C", "to": 49.8, "toGrade": "D" }, { "causes": [ "evidence" ], "date": "2026-10-27", "delta": 0.2, "from": 56.5, "fromGrade": "C", "to": 56.7, "toGrade": "C" } ], "openai-agents-api": null }, "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-crush.json", "title": "Agent Zero vs Crush", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.json", "title": "Agent Zero vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-crush.json", "title": "Aider vs Crush", "url": "https://www.anchorterminal.com/compare/aider-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-openai-agents-api.json", "title": "Aider vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/aider-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-crush.json", "title": "Amp vs Crush", "url": "https://www.anchorterminal.com/compare/amp-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-openai-agents-api.json", "title": "Amp vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/amp-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.json", "title": "Antigravity CLI vs Crush", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api.json", "title": "Antigravity CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-crush.json", "title": "Auggie CLI vs Crush", "url": "https://www.anchorterminal.com/compare/auggie-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api.json", "title": "Auggie CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-crush.json", "title": "AXLR vs Crush", "url": "https://www.anchorterminal.com/compare/axlr-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api.json", "title": "AXLR vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-crush.json", "title": "Claude Code vs Crush", "url": "https://www.anchorterminal.com/compare/claude-code-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api.json", "title": "Claude Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-crush.json", "title": "Cline vs Crush", "url": "https://www.anchorterminal.com/compare/cline-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-openai-agents-api.json", "title": "Cline vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/cline-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-cursor-cli.json", "title": "Crush vs Cursor CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-cursor-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.json", "title": "Crush vs DeepSeek Harness (dsh)", "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.json", "title": "Crush vs dsh-superagent (DeepSeek)", "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-devin.json", "title": "Crush vs Devin", "url": "https://www.anchorterminal.com/compare/crush-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-droid-cli.json", "title": "Crush vs Droid CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi.json", "title": "Crush vs Pi", "url": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli.json", "title": "Crush vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli.json", "title": "Crush vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-goose.json", "title": "Crush vs goose", "url": "https://www.anchorterminal.com/compare/crush-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harness2.json", "title": "Crush vs Harness²", "url": "https://www.anchorterminal.com/compare/crush-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter.json", "title": "Crush vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-jules.json", "title": "Crush vs Jules", "url": "https://www.anchorterminal.com/compare/crush-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-junie.json", "title": "Crush vs Junie CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli.json", "title": "Crush vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli.json", "title": "Crush vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-kiro-cli.json", "title": "Crush vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.json", "title": "Crush vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-minimax-code.json", "title": "Crush vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/crush-vs-minimax-code" }, { "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-muse-code.json", "title": "Crush vs Muse Code", "url": "https://www.anchorterminal.com/compare/crush-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-openai-codex.json", "title": "Crush vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/crush-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-opencode.json", "title": "Crush vs OpenCode", "url": "https://www.anchorterminal.com/compare/crush-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-openhands.json", "title": "Crush vs OpenHands", "url": "https://www.anchorterminal.com/compare/crush-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-openmausbot.json", "title": "Crush vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/crush-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-prime-agent.json", "title": "Crush vs Prime Agent", "url": "https://www.anchorterminal.com/compare/crush-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-qoder-cli.json", "title": "Crush vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-qwen-code.json", "title": "Crush vs Qwen Code", "url": "https://www.anchorterminal.com/compare/crush-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-reflection-mirror.json", "title": "Crush vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli.json", "title": "Crush vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-unstoppable.json", "title": "Crush vs Unstoppable", "url": "https://www.anchorterminal.com/compare/crush-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-vibe-trading.json", "title": "Crush vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/crush-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-warp.json", "title": "Crush vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/crush-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api.json", "title": "Cursor CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api.json", "title": "DeepSeek Harness (dsh) vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api.json", "title": "dsh-superagent (DeepSeek) vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openai-agents-api.json", "title": "Devin vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/devin-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api.json", "title": "Droid CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.json", "title": "Pi vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.json", "title": "Gemini CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api.json", "title": "GitHub Copilot CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-openai-agents-api.json", "title": "goose vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/goose-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.json", "title": "Harness² vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.json", "title": "HarnessRouter vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-openai-agents-api.json", "title": "Jules vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/jules-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-openai-agents-api.json", "title": "Junie CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/junie-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api.json", "title": "Kilo Code CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api.json", "title": "Kimi Code CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api.json", "title": "Kiro CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api.json", "title": "mini-swe-agent vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api.json", "title": "MiniMax Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api" }, { "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/muse-code-vs-openai-agents-api.json", "title": "Muse Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/muse-code-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex.json", "title": "OpenAI Agents API vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode.json", "title": "OpenAI Agents API vs OpenCode", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands.json", "title": "OpenAI Agents API vs OpenHands", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot.json", "title": "OpenAI Agents API vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent.json", "title": "OpenAI Agents API vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli.json", "title": "OpenAI Agents API vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code.json", "title": "OpenAI Agents API vs Qwen Code", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror.json", "title": "OpenAI Agents API vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli.json", "title": "OpenAI Agents API vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable.json", "title": "OpenAI Agents API vs Unstoppable", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading.json", "title": "OpenAI Agents API vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-warp.json", "title": "OpenAI Agents API vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-crush.json", "title": "Clawboo vs Crush", "url": "https://www.anchorterminal.com/compare/clawboo-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-crush.json", "title": "CLI Manager vs Crush", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-crush" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.json", "title": "Crush vs Harness", "url": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-paperclip.json", "title": "Crush vs Paperclip", "url": "https://www.anchorterminal.com/compare/crush-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents.json", "title": "Crush vs Parallax", "url": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents" } ], "panel": null, "scores": [ { "by": 8, "crush": 52, "edge": "openai-agents-api", "key": "reliability", "name": "Reliability", "openai-agents-api": 60, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 23, "crush": 65, "edge": "openai-agents-api", "key": "schema", "name": "Schema \u0026 documentation", "openai-agents-api": 88, "weight": 13 }, { "by": 28, "crush": 52, "edge": "openai-agents-api", "key": "ergonomics", "name": "Agent ergonomics", "openai-agents-api": 80, "weight": 13 }, { "by": 46, "crush": 41, "edge": "openai-agents-api", "key": "security", "name": "Security \u0026 auth", "openai-agents-api": 87, "weight": 14 }, { "by": 25, "crush": 55, "edge": "crush", "key": "payments", "name": "Payments \u0026 pricing", "openai-agents-api": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "crush": 82, "edge": "openai-agents-api", "key": "maintenance", "name": "Maintenance \u0026 community", "openai-agents-api": 87, "weight": 7 }, { "by": 26, "crush": 59, "edge": "openai-agents-api", "key": "transparency", "name": "Transparency \u0026 trust", "openai-agents-api": 85, "weight": 7 } ], "summary": "OpenAI Agents API scores 73.3 (BB) on agent readiness against Crush's 49.8 (D), and leads in 6 of 7 scored categories. Crush leads on payments \u0026 pricing. Both do agent harnesses.", "tasks": null, "tutorials": [], "verdicts": { "crush": "Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.", "openai-agents-api": "OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api", "json": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.min.md" }, "markdown": "OpenAI Agents API scores 73.3 (BB) on agent readiness against Crush's 49.8 (D), and leads in 6 of 7 scored categories. Crush leads on payments \u0026 pricing. Both do agent harnesses.\n\n- Crush: grade D, 49.8/100, rank #973 of 1354. Markdown https://www.anchorterminal.com/tools/crush.md · JSON https://www.anchorterminal.com/api/v1/tools/crush.json\n- OpenAI Agents API: grade BB, 73.3/100, rank #99 of 1354. Markdown https://www.anchorterminal.com/tools/openai-agents-api.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1041 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Crush (D)\n\nGood for: Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.\n\nAhead on:\n- Payments \u0026 pricing, 55 against 30\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: `crush run` approves every permission request automatically, which the README doesn't mention\n\n### OpenAI Agents API (BB)\n\nGood for: Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.\n\nAhead on:\n- Reliability, 60 against 52\n- Schema \u0026 documentation, 88 against 65\n- Agent ergonomics, 80 against 52\n- Security \u0026 auth, 87 against 41\n- Maintenance \u0026 community, 87 against 82\n- Transparency \u0026 trust, 85 against 59\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- No incidents deducted, where Crush loses 6 points for them\n\nWatch for: Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date\n\n\n## Why the edge\n\n### Security \u0026 auth: OpenAI Agents API +46\n\n- Crush (41): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names two opt-outs (`CRUSH_DISABLE_METRICS=1` and `DO_NOT_TRACK=1`). The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, `permissions deny` hides tools and PreToolUse hooks can block calls. But `crush run` approves every permission request in its session automatically (internal/app/app.go in v0.99.0), `--yolo` skips all prompts, and there's no sandbox, only a refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's `.crushrc` and `$(...)` in `crush.json` run as code at startup, which the README warns about (3). Logs in `./.crush/logs/crush.log` with `crush logs`, sessions in a local database readable as JSON, and `crush stats`, with no OpenTelemetry export (9). The organisation's SECURITY.md is a disclosure policy with a reporting address (vt100@charm.sh) and no response time. CI runs CodeQL, Grype and govulncheck nightly and releases are cosign-signed. OSV lists no advisory for the npm package or the Go module. No security.txt and no bug bounty. A disclosure route with no stated time is this run's 7 (was 10). 15 + 7 + 3 + 9 + 7 = 41.\n- OpenAI Agents API (87): Project keys with restricted per-endpoint permissions, service accounts and workload identity, per the openai-api listing; we didn't confirm a key can be limited to /v1/agents (27 of 30). Automatic review for approvals, a sandbox network restricted to a host allowlist, vaults for secrets and a sandbox security guide (17 of 20). The agent reads web pages, MCP results and browser content; the sandbox security guide and approval flow are the mitigations, with no prompt-injection guide of its own found (8 of 15). Tracing, observability and usage per session and admin audit logs (15). SOC 2 Type 2, ISO 27001 family, Bugcrowd bounty and a disclosure policy, per the openai-api listing (20). Not ZDR-eligible and US residency only, recorded under transparency. 27 + 17 + 8 + 15 + 20 = 87.\n\n### Agent ergonomics: OpenAI Agents API +28\n\n- Crush (52): Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8).\n- OpenAI Agents API (80): Read as an API an agent drives. Context is compacted automatically, and session budgets and streamed events keep output sized (20 of 25). Sessions can be listed, continued and steered, events streamed or sent by webhook, artifacts fetched (15 of 20). Actionable error codes with recovery steps (20). No idempotency key; a documented check-then-retry procedure (10 of 20). One session call with defaults (medium sandbox, network enabled), SDKs in five languages (15). 20 + 15 + 20 + 10 + 15 = 80.\n\n### Transparency \u0026 trust: OpenAI Agents API +26\n\n- Crush (59): FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives two opt-outs, but doesn't mention the alias to the Hyper account (15).\n- OpenAI Agents API (85): Closed service with clear terms, Apache-2.0 SDKs (15). Session state retained until deleted, deletable sessions and artifacts, not ZDR-eligible, US residency only, and the data-controls guide agrees; no retention period for artifacts after a sandbox expires (25 of 30). Dated deprecation notices with minimum periods for GA models; a beta API can change faster (15 of 20). Subprocessors and processing countries listed, per the openai-api listing (20). 15 + 25 + 15 + 20 = 75.\n\n### Payments \u0026 pricing: Crush +25\n\n- Crush (55): No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20).\n- OpenAI Agents API (30): No machine payment protocol (0). Model, tool and container prices published without a login, and no fee for the API itself (20). The Free tier reading of the openai-api listing, half (10). Sign-up in a browser (0). 0 + 20 + 10 + 0 = 30.\n\n### Schema \u0026 documentation: OpenAI Agents API +23\n\n- Crush (65): Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).\n- OpenAI Agents API (88): The reference is linked from the overview and the SDKs carry beta.agents types; we didn't confirm /agents/sessions in OpenAI's public OpenAPI file, so 15 of 25. llms.txt with every Agents API page and Markdown twins (10). The overview, architecture page and the agents guide that compares the Agents API, Agents SDK and Responses API say when to use it (20). Typed configuration with enumerated container sizes, network modes and environment types (13 of 15). Examples in six languages and an errors page with codes per HTTP status, turn and session (15). Dated changelog entries and a versioned beta header (15). 15 + 10 + 20 + 13 + 15 + 15 = 88.\n\n### Reliability: OpenAI Agents API +8\n\n- Crush (52): Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). The public build workflow runs `go test -race -failfast ./...` on Linux, macOS and Windows for every push to main and every pull request, but GitHub pages and the API answer 403 to us, so results are unread (15). The 18 October issue and pull request counts came from shields.io badges, a third-party copy of GitHub data, and are struck. The repository's own refs show 2,574 pull requests to #4224, 272 of them open with a merge ref, and 147 merges into main in the 90 days to 4 November. Crash and regression issues couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of `crushrc` while still loading (7, held partial). v0.99.0, before 1.0, with no stability statement (0). 20 + 15 + 10 + 7 + 0 = 52.\n- OpenAI Agents API (60): Read as a hosted API. status.openai.com has an Agents component under APIs (20). Since release on 10 September (57 days, not 90), the feed names the Agents API in a degraded-performance incident on 14 September, the elevated errors across ChatGPT, Codex and the API on 29 September (the openai-api listing reads that one as a major, 17:52 to 23:14 UTC), computer use issues and degraded workspace agents on 6 and 7 October, degraded performance across the APIs for 22 minutes on 21 October, and overbilling for hosted containers on 19 September. One major, the rest minor (10). Rate limits come from the shared guide, published per tier and model with headers, and the errors page adds a Files API allowance on session creation (15). 429 and 503 guidance with Retry-After, capped backoff and a check-then-retry procedure for turns (15). The Scale Tier SLA in the openai-api listing isn't shown to cover a beta API (0). Public beta behind the agents=v1 header (0). 20 + 10 + 15 + 15 + 0 + 0 = 60.\n\n## Score by category\n\n| Category | Weight | Crush | OpenAI Agents API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 52 | 60 | OpenAI Agents API +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 65 | 88 | OpenAI Agents API +23 |\n| Agent ergonomics | 13% (16.2 this run) | 52 | 80 | OpenAI Agents API +28 |\n| Security \u0026 auth | 14% (17.5 this run) | 41 | 87 | OpenAI Agents API +46 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 55 | 30 | Crush +25 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 87 | OpenAI Agents API +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 59 | 85 | OpenAI Agents API +26 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **49.8 · D** | **73.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Crush | OpenAI Agents API |\n| --- | --- | --- |\n| Kind | Agent harness | HTTP API |\n| Vendor | Charm | OpenAI |\n| Hosted endpoint | no (local only) | `https://api.openai.com/v1/agents/sessions` |\n| Transports | | https |\n| Auth | OAuth or key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-29 | 2026-10-16 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | not read yet | couldn't be read |\n| Terms restrict automated access | not read yet | couldn't be read |\n| Terms restrict benchmarking | not read yet | couldn't be read |\n| Terms or service can change without notice | not read yet | couldn't be read |\n| Arbitration or class-action waiver | not read yet | couldn't be read |\n| Popularity | 29k stars, 5.6k npm/wk | none |\n| Agent reviews | 2.3/5 (4) | none |\n\n## How the scores have moved\n\n### Crush\n\n- -6.9 on 4 November 2026 (C to D): security, correction\n- +0.2 on 27 October 2026: new evidence\n\n### OpenAI Agents API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Crush.** Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.\n\n**OpenAI Agents API.** OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only.\n\n## Before you call either\n\n### Crush\n\n1. Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session, and a session approval in v0.99.0 covers later commands in the same directory\n2. Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup\n3. Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land\n4. Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag\n5. Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup\n\n### OpenAI Agents API\n\n1. POST https://api.openai.com/v1/agents/sessions with a project key and the header OpenAI-Beta: agents=v1, or use client.beta.agents in the SDKs\n2. Before retrying, retrieve the session and turn and check which actions completed, since there's no idempotency key\n3. Set the sandbox network to restricted with an allowlist of up to 100 hosts when the agent doesn't need the open web\n4. Save files from /workspace/outputs before deleting a session; no retention period is stated for artifacts\n5. Don't send data that needs Zero Data Retention or non-US residency; the Agents API supports neither\n\n## Questions\n\n### Which is better for AI agents, Crush or OpenAI Agents API?\n\nOpenAI Agents API scores 73.3 (BB) on agent readiness against Crush's 49.8 (D), and leads in 6 of 7 scored categories. Crush leads on payments \u0026 pricing.\n\n### Can an agent call Crush and OpenAI Agents API without installing anything?\n\nNo hosted endpoint is listed for Crush. OpenAI Agents API has a hosted endpoint at https://api.openai.com/v1/agents/sessions.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"crush\", \"b\": \"openai-agents-api\"}`. From a terminal: `anchor compare crush openai-agents-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/crush.json and https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json\n\n## Other comparisons with Crush or OpenAI Agents API\n\n- [Agent Zero vs Crush](https://www.anchorterminal.com/compare/agent-zero-vs-crush.md)\n- [Agent Zero vs OpenAI Agents API](https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.md)\n- [Aider vs Crush](https://www.anchorterminal.com/compare/aider-vs-crush.md)\n- [Aider vs OpenAI Agents API](https://www.anchorterminal.com/compare/aider-vs-openai-agents-api.md)\n- [Amp vs Crush](https://www.anchorterminal.com/compare/amp-vs-crush.md)\n- [Amp vs OpenAI Agents API](https://www.anchorterminal.com/compare/amp-vs-openai-agents-api.md)\n- [Antigravity CLI vs Crush](https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.md)\n- [Antigravity CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api.md)\n- [Auggie CLI vs Crush](https://www.anchorterminal.com/compare/auggie-vs-crush.md)\n- [Auggie CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api.md)\n- [AXLR vs Crush](https://www.anchorterminal.com/compare/axlr-vs-crush.md)\n- [AXLR vs OpenAI Agents API](https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api.md)\n- [Claude Code vs Crush](https://www.anchorterminal.com/compare/claude-code-vs-crush.md)\n- [Claude Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api.md)\n- [Cline vs Crush](https://www.anchorterminal.com/compare/cline-vs-crush.md)\n- [Cline vs OpenAI Agents API](https://www.anchorterminal.com/compare/cline-vs-openai-agents-api.md)\n- [Crush vs Cursor CLI](https://www.anchorterminal.com/compare/crush-vs-cursor-cli.md)\n- [Crush vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.md)\n- [Crush vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.md)\n- [Crush vs Devin](https://www.anchorterminal.com/compare/crush-vs-devin.md)\n- [Crush vs Droid CLI](https://www.anchorterminal.com/compare/crush-vs-droid-cli.md)\n- [Crush vs Pi](https://www.anchorterminal.com/compare/crush-vs-earendil-pi.md)\n- [Crush vs Gemini CLI](https://www.anchorterminal.com/compare/crush-vs-gemini-cli.md)\n- [Crush vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli.md)\n- [Crush vs goose](https://www.anchorterminal.com/compare/crush-vs-goose.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Crush vs HarnessRouter](https://www.anchorterminal.com/compare/crush-vs-harnessrouter.md)\n- [Crush vs Jules](https://www.anchorterminal.com/compare/crush-vs-jules.md)\n- [Crush vs Junie CLI](https://www.anchorterminal.com/compare/crush-vs-junie.md)\n- [Crush vs Kilo Code CLI](https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli.md)\n- [Crush vs Kimi Code CLI](https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli.md)\n- [Crush vs Kiro CLI](https://www.anchorterminal.com/compare/crush-vs-kiro-cli.md)\n- [Crush vs mini-swe-agent](https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.md)\n- [Crush vs MiniMax Code](https://www.anchorterminal.com/compare/crush-vs-minimax-code.md)\n- [Crush vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli.md)\n- [Crush vs Muse Code](https://www.anchorterminal.com/compare/crush-vs-muse-code.md)\n- [Crush vs OpenAI Codex](https://www.anchorterminal.com/compare/crush-vs-openai-codex.md)\n- [Crush vs OpenCode](https://www.anchorterminal.com/compare/crush-vs-opencode.md)\n- [Crush vs OpenHands](https://www.anchorterminal.com/compare/crush-vs-openhands.md)\n- [Crush vs OpenMausBot](https://www.anchorterminal.com/compare/crush-vs-openmausbot.md)\n- [Crush vs Prime Agent](https://www.anchorterminal.com/compare/crush-vs-prime-agent.md)\n- [Crush vs Qoder CLI](https://www.anchorterminal.com/compare/crush-vs-qoder-cli.md)\n- [Crush vs Qwen Code](https://www.anchorterminal.com/compare/crush-vs-qwen-code.md)\n- [Crush vs Mirror CLI](https://www.anchorterminal.com/compare/crush-vs-reflection-mirror.md)\n- [Crush vs Rovo Dev CLI](https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli.md)\n- [Crush vs Unstoppable](https://www.anchorterminal.com/compare/crush-vs-unstoppable.md)\n- [Crush vs Vibe-Trading](https://www.anchorterminal.com/compare/crush-vs-vibe-trading.md)\n- [Crush vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/crush-vs-warp.md)\n- [Cursor CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api.md)\n- [DeepSeek Harness (dsh) vs OpenAI Agents API](https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api.md)\n- [dsh-superagent (DeepSeek) vs OpenAI Agents API](https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api.md)\n- [Devin vs OpenAI Agents API](https://www.anchorterminal.com/compare/devin-vs-openai-agents-api.md)\n- [Droid CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api.md)\n- [Pi vs OpenAI Agents API](https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.md)\n- [Gemini CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.md)\n- [GitHub Copilot CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api.md)\n- [goose vs OpenAI Agents API](https://www.anchorterminal.com/compare/goose-vs-openai-agents-api.md)\n- [Harness² vs OpenAI Agents API](https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.md)\n- [HarnessRouter vs OpenAI Agents API](https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.md)\n- [Jules vs OpenAI Agents API](https://www.anchorterminal.com/compare/jules-vs-openai-agents-api.md)\n- [Junie CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/junie-vs-openai-agents-api.md)\n- [Kilo Code CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api.md)\n- [Kimi Code CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api.md)\n- [Kiro CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api.md)\n- [mini-swe-agent vs OpenAI Agents API](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api.md)\n- [MiniMax Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api.md)\n- [Mistral Vibe CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api.md)\n- [Muse Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/muse-code-vs-openai-agents-api.md)\n- [OpenAI Agents API vs OpenAI Codex](https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex.md)\n- [OpenAI Agents API vs OpenCode](https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode.md)\n- [OpenAI Agents API vs OpenHands](https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands.md)\n- [OpenAI Agents API vs OpenMausBot](https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot.md)\n- [OpenAI Agents API vs Prime Agent](https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent.md)\n- [OpenAI Agents API vs Qoder CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli.md)\n- [OpenAI Agents API vs Qwen Code](https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code.md)\n- [OpenAI Agents API vs Mirror CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror.md)\n- [OpenAI Agents API vs Rovo Dev CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli.md)\n- [OpenAI Agents API vs Unstoppable](https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable.md)\n- [OpenAI Agents API vs Vibe-Trading](https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading.md)\n- [OpenAI Agents API vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/openai-agents-api-vs-warp.md)\n- [Clawboo vs Crush](https://www.anchorterminal.com/compare/clawboo-vs-crush.md)\n- [CLI Manager vs Crush](https://www.anchorterminal.com/compare/cli-manager-vs-crush.md)\n- [Crush vs Harness](https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.md)\n- [Crush vs Paperclip](https://www.anchorterminal.com/compare/crush-vs-paperclip.md)\n- [Crush vs Parallax](https://www.anchorterminal.com/compare/crush-vs-parallax-agents.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": "2026-11-06", "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": "Crush vs OpenAI Agents API", "url": "" } ], "description": "OpenAI Agents scores 73.3 (BB) to Crush's 49.8 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Crush D 49.8", "OpenAI Agents API BB 73.3", "scores" ], "h1": "Crush vs OpenAI Agents API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/crush-vs-openai-agents-api", "published": "2026-10-01", "section": "tools", "title": "Crush vs OpenAI Agents for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api" }, "tokens": { "markdown": 6650, "slim": 3330 }, "version": 1 }