{ "data": { "a": { "slug": "earendil-pi", "name": "Pi", "vendor": "Earendil", "vendorUrl": "https://pi.dev", "kind": "harness", "category": "agent-harnesses", "summary": "Pi is an open-source terminal coding agent from Earendil, run on the owner's machine with any of 15 or more model providers. It has interactive, print, JSON and RPC modes, a TypeScript SDK and a built-in MCP client.", "url": "https://www.anchorterminal.com/tools/earendil-pi", "markdownUrl": "https://www.anchorterminal.com/tools/earendil-pi.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/earendil-pi.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/earendil-pi.json", "repo": "https://github.com/earendil-works/pi", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@earendil-works/pi-coding-agent" } ], "auth": "none", "authNotes": "No Pi account needed. Model providers are connected with `/login` (a subscription or an API key, stored in `~/.pi/agent/auth.json`) or with environment variables such as `ANTHROPIC_API_KEY`. MCP servers take headers, bearer tokens from the environment or OAuth, with tokens kept in `~/.pi/agent/mcp-auth.json`. Radius, the optional hosted gateway, needs its own sign-in or `RADIUS_API_KEY`.", "pricing": "free", "pricingNotes": "Free and MIT, with no paid edition of the harness. The owner pays the model provider. Radius, Earendil's optional hosted gateway, is an early alpha sold by prepaid credits, and no public price list was found (checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository or the docs (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 113417, "npmWeekly": 5201697, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://pi.dev/docs/latest", "capabilities": [ "agent.harness", "agent.mcp-client" ], "tags": [ "open-source", "local", "free", "no-card", "typescript", "mcp", "json-output", "rpc", "no-sandbox" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 68.4, "grade": "B", "agentReady": false, "rank": 203, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 87, "payments": 60, "reliability": 75, "schema": 84, "security": 61, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -4, "negativeNotes": [ "2026-06-08. GHSA-jfgx-wxx8-mp94 (CVE-2026-54328, high). Temporary extension installs used predictable paths under the system temp directory, so another local user on a shared Linux host could plant extension code that Pi then loaded. Fixed in 0.78.1. Fixed, published and four months old, -2. https://github.com/earendil-works/pi/security/advisories/GHSA-jfgx-wxx8-mp94", "2026-06-08. GHSA-mqxh-6gq7-558m (CVE-2026-54325, medium). Before 0.79.0 Pi loaded a repository's `.pi` settings and extensions without asking, so starting it in a cloned repository could run that repository's code. Fixed in 0.79.0 with project trust. Fixed and published, -2. https://github.com/earendil-works/pi/security/advisories/GHSA-mqxh-6gq7-558m", "2026-06-08. GHSA-7v5m-pr3q-6453 (CVE-2026-54326, low, XSS in HTML session exports) and GHSA-r95r-rj6r-c39x (CVE-2026-54327, low, a race in `auth.json` permissions). Both fixed in 0.78.1. Recorded without a deduction. https://github.com/earendil-works/pi/security/advisories" ], "verdict": "Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.0.0 is dated 1 October 2026.", "bestFor": "Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.", "strengths": [ "Four default tools (read, bash, edit, write), with MCP tools reachable through codemode scripts and not declared to the model by default", "`--mode json` streams JSONL events and `--mode rpc` takes JSONL commands, both documented record by record, with a Python client example", "Built-in MCP client for stdio and streamable HTTP servers with OAuth, per-tool exposure settings and a conformance job in CI", "Project trust stops a repository's `.pi` settings, extensions and MCP servers loading until approved, and non-interactive modes skip them by default", "npm releases carry SLSA provenance from GitHub Actions trusted publishing, and the installer pins transitive dependencies" ], "weaknesses": [ "No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt", "An anonymous install and update ping to pi.dev and a latest-version request are on by default", "Four advisories published on 8 June 2026, one rated high and one medium, all fixed by 0.79.0", "No privacy policy for pi.dev or the CLI found, and pi.dev has no security.txt", "Eight of the last 15 CI runs on main failed on 7 and 8 October 2026, and a breaking provider rename shipped in patch release 1.0.3" ], "agentNotes": [ "Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands", "Use `pi --mode json` and wait for `agent_settled`. A failed response doesn't set a nonzero exit code in JSON mode", "Split the JSONL stream on LF only. Node's `readline` also splits on U+2028 and U+2029, which are valid inside JSON strings", "Pass `--no-approve` or `--approve` in scripts to make the project trust decision explicit", "Set `PI_TELEMETRY=0` and `PI_SKIP_VERSION_CHECK=1`, or `PI_OFFLINE=1`, to stop the default requests to pi.dev" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68.4 } ], "editorialScores": { "ergonomics": 76, "maintenance": 87, "payments": 60, "reliability": 75, "schema": 84, "security": 61, "transparency": 64 }, "provenanceScore": 63 }, "connect": { "install": "curl -fsSL https://pi.dev/install.sh | sh # or: npm install -g --ignore-scripts @earendil-works/pi-coding-agent", "headless": { "command": "pi --mode json --no-session --no-approve \"$TASK\"", "env": { "PI_SKIP_VERSION_CHECK": "1", "PI_TELEMETRY": "0" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/earendil-pi" }, "area": "frameworks", "provenance": { "legalEntity": "Earendil Inc.", "domain": "pi.dev", "domainRegistered": "2024-01-30", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://pi.dev/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The pi.dev and earendil.com footers read Earendil Inc. The Radius alpha terms of 1 September 2026 name Earendil Works Co., and the README calls the company Earendil Works.", "We found no terms or privacy page for pi.dev or the CLI. pi.dev/terms, pi.dev/privacy and earendil.com/privacy return 404. Terms exist only for Radius, at radius.earendil.com/terms.", "pi.dev/.well-known/security.txt and earendil.com/.well-known/security.txt return 404. SECURITY.md gives security@earendil.com and GitHub private reporting.", "RDAP for pi.dev gives a registration date of 2024-01-30 with Cloudflare as registrar. The README says the domain was donated by exe.dev.", "The repository moved from badlogic/pi-mono to earendil-works/pi, and the npm package from @mariozechner/pi-coding-agent to @earendil-works/pi-coding-agent at 0.74.0, per the advisories." ], "score": 63 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/earendil-pi.json", "live": { "slug": "earendil-pi", "versions": [ { "registry": "github", "name": "earendil-works/pi", "version": "v1.1.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:09:44.573412777Z" }, { "registry": "npm", "name": "@earendil-works/pi-coding-agent", "version": "1.1.0", "seenAt": "2026-10-08T16:09:41.369786574Z" } ], "githubStars": 113482, "npmWeekly": 5201697, "securityTxt": { "url": "https://pi.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:42.51766104Z" }, "pages": [ { "url": "https://pi.dev/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:22:53.741589246Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "82f9cb8bddf7" } ], "updatedAt": "2026-10-08T18:22:53.741589246Z" } }, "answer": "OpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability.", "b": { "slug": "openai-codex", "name": "OpenAI Codex", "vendor": "OpenAI", "vendorUrl": "https://openai.com", "kind": "harness", "category": "agent-harnesses", "summary": "OpenAI's coding agent for software development tasks.", "url": "https://www.anchorterminal.com/tools/openai-codex", "markdownUrl": "https://www.anchorterminal.com/tools/openai-codex.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openai-codex.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openai-codex.json", "repo": "https://github.com/openai/codex", "license": "Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms", "transports": [], "packages": [ { "registry": "npm", "name": "@openai/codex" } ], "auth": "mixed", "authNotes": "Sign in with a ChatGPT account (Free, Go, Plus, Pro, Business, Edu or Enterprise) or use an OpenAI API key. Cloud work such as GitHub code review and the Slack integration comes with Plus and above, and none of it works with an API key. `--oss` talks to a local Ollama or LM Studio server and needs no account.", "pricing": "freemium", "pricingNotes": "Included in every ChatGPT plan. Free $0, Go $8 a month, Plus $20, Pro from $100 (tiers at $100, $200 and $500), Business $20 a user a month billed annually for two or more users, Enterprise and Edu by quote. On Plus the docs estimate 15 to 160 local messages per five hours with GPT-6.1 Sol, and Pro has no five-hour limit. Cloud tasks use more of the allowance. With an API key you pay API token rates and can't use the cloud agent (checked 2026-10-02).", "priceSummary": "$20 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the pricing page or the source (checked 2026-10-02).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 126000, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://developers.openai.com/codex", "llmsTxt": "https://learn.chatgpt.com/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client" ], "tags": [ "official", "harness", "coding-agent", "cli", "open-source", "rust", "typescript", "python", "mcp", "llms-txt", "telemetry-default-on", "pre-1.0", "free-tier", "no-card", "hosted", "status-page" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 73, "grade": "BB", "agentReady": true, "rank": 92, "ranked": true, "rankOf": 842, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 87, "payments": 60, "reliability": 55, "schema": 90, "security": 82, "transparency": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -2, "negativeNotes": [ "2026-04-14. CVE-2025-61260 (GHSA-xrxf-jgv3-qmrm), critical (CVSS 9.8 from CISA-ADP), code execution through MCP configuration files in a repository for Codex CLI 0.23.0 and earlier, published to NVD and the GitHub Advisory Database from Check Point Research's 2025 report. Fixed in 2025 and documented by the researcher, with no advisory in OpenAI's own repository, so a small deduction (https://nvd.nist.gov/vuln/detail/CVE-2025-61260; https://research.checkpoint.com/2025/openai-codex-cli-command-injection-vulnerability/)" ], "verdict": "Sandbox on by default on macOS, Linux and Windows, with the network off and `.git` and `.codex` read-only. Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes.", "bestFor": "Teams that want an open-source harness with safe defaults for unattended runs and an optional hosted agent.", "strengths": [ "Sandbox on by default on macOS, Linux and Windows, with the network off and `.git` and `.codex` read-only", "Apache-2.0, with public CI and a JSON Schema for config.toml", "`codex exec --json`, `--output-schema` and `exec resume` for pipelines, plus TypeScript and Python SDKs", "Codex cloud keeps the agent phase offline by default and can limit requests to GET, HEAD and OPTIONS", "Included in ChatGPT Free, and `--oss` runs local models through Ollama or LM Studio with no account" ], "weaknesses": [ "Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes", "Anonymous usage metrics and feedback collection on by default", "Over 5,000 open issues", "CVE-2025-61260 (critical) has no advisory in OpenAI's own repository", "Cloud tasks and code review need a ChatGPT plan, not an API key" ], "agentNotes": [ "Run `codex exec --json` in pipelines, with `--output-schema` when the final message has to parse", "Keep the default sandbox. `--yolo` removes both the sandbox and approvals", "Set `network_access = true` under `[sandbox_workspace_write]` only for tasks that need it. Network is off by default", "Set `[analytics] enabled = false` and `[feedback] enabled = false` in config.toml to keep usage data local", "Pin the npm version. A 0.x minor lands every few days" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73 } ], "editorialScores": { "ergonomics": 80, "maintenance": 87, "payments": 60, "reliability": 55, "schema": 90, "security": 82, "transparency": 65 }, "provenanceScore": 93 }, "connect": { "install": "npm i -g @openai/codex # or: brew install --cask codex", "headless": { "run": "codex exec --json \"fix the failing test\"" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/openai-codex" }, "sameCompany": [ "openai-api", "openai-embeddings", "openai-guardrails", "openai-moderation", "openai-image-api", "openai-sora", "openai-agents-sdk", "openai-decisions-api" ], "area": "frameworks", "unitPrices": [ { "item": "ChatGPT Plus", "unit": "month", "usd": 20, "note": "includes Codex local and cloud" }, { "item": "ChatGPT Pro", "unit": "month", "usd": 100, "note": "lowest Pro tier, no five-hour limit" } ], "provenance": { "legalEntity": "OpenAI OpCo, LLC", "domain": "openai.com", "domainRegistered": "2007-01-19", "endpointOnVendorDomain": null, "terms": "https://openai.com/policies/services-agreement/", "privacy": "https://openai.com/policies/privacy-policy/", "statusPage": "https://status.openai.com", "changelog": "https://github.com/openai/codex/releases", "securityTxt": "valid", "checked": "2026-10-01", "notes": [ "The Codex docs moved from developers.openai.com/codex to learn.chatgpt.com (302 redirects on 2 October 2026), and the installer is served from chatgpt.com.", "Legal entity, domain date and security.txt are from the openai-api listing's check of 26 September 2026." ], "score": 93 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/openai-codex.json", "live": { "slug": "openai-codex", "vendorStatus": { "page": "https://status.openai.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T15:31:01.192801293Z" }, "versions": [ { "registry": "github", "name": "openai/codex", "version": "rust-v0.161.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:23:35.402162465Z" }, { "registry": "npm", "name": "@openai/codex", "version": "0.161.0", "seenAt": "2026-10-08T16:23:35.110125025Z" } ], "githubStars": 128364, "npmWeekly": 25613321, "securityTxt": { "url": "https://openai.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-08T15:38:50.073851341Z" }, "llmsTxt": { "url": "https://learn.chatgpt.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:02:29.098513433Z" }, "domain": { "domain": "openai.com", "registered": "2007-01-19", "source": "https://rdap.verisign.com/com/v1/domain/openai.com", "checkedAt": "2026-10-04T13:05:02.32020521Z" }, "updatedAt": "2026-10-09T15:31:01.192801293Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Earendil", "b": "OpenAI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-07", "b": "2026-10-01", "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": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "113k stars, 5.2M npm/wk", "b": "126k stars", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "OpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability.", "question": "Which is better for AI agents, Pi or OpenAI Codex?" }, { "answer": "Yes. Pi is open source (MIT). OpenAI Codex is open source (Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms).", "question": "Are Pi and OpenAI Codex open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 75 against 55" ], "also": [ "No key needed to call it" ], "goodFor": "Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.", "slug": "earendil-pi", "watchFor": "No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt" }, { "aheadOn": [ "Schema \u0026 documentation, 90 against 84", "Security \u0026 auth, 82 against 61", "Transparency \u0026 trust, 79 against 64" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Teams that want an open-source harness with safe defaults for unattended runs and an optional hosted agent.", "slug": "openai-codex", "watchFor": "Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes" } ], "job": { "capability": "agent.harness", "name": "Agent harness" }, "others": [ { "json": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi.json", "title": "Aider vs Pi", "url": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-openai-codex.json", "title": "Aider vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/aider-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-earendil-pi.json", "title": "Amp vs Pi", "url": "https://www.anchorterminal.com/compare/amp-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-openai-codex.json", "title": "Amp vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/amp-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.json", "title": "Claude Code vs Pi", "url": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.json", "title": "Claude Code vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-earendil-pi.json", "title": "Cline vs Pi", "url": "https://www.anchorterminal.com/compare/cline-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-openai-codex.json", "title": "Cline vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/cline-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.json", "title": "Cursor CLI vs Pi", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-codex.json", "title": "Cursor CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi.json", "title": "Devin vs Pi", "url": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openai-codex.json", "title": "Devin vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/devin-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.json", "title": "Pi vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli.json", "title": "Pi vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-goose.json", "title": "Pi vs goose", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.json", "title": "Pi vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.json", "title": "Pi vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-opencode.json", "title": "Pi vs OpenCode", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.json", "title": "Pi vs OpenHands", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.json", "title": "Pi vs Prime Agent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.json", "title": "Pi vs Qwen Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex.json", "title": "Gemini CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-codex.json", "title": "GitHub Copilot CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-openai-codex.json", "title": "goose vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/goose-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex.json", "title": "Kilo Code CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex.json", "title": "Kiro CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-opencode.json", "title": "OpenAI Codex vs OpenCode", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-openhands.json", "title": "OpenAI Codex vs OpenHands", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.json", "title": "OpenAI Codex vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-qwen-code.json", "title": "OpenAI Codex vs Qwen Code", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-qwen-code" } ], "scores": [ { "by": 20, "earendil-pi": 75, "edge": "earendil-pi", "key": "reliability", "name": "Reliability", "openai-codex": 55, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 6, "earendil-pi": 84, "edge": "openai-codex", "key": "schema", "name": "Schema \u0026 documentation", "openai-codex": 90, "weight": 13 }, { "by": 4, "earendil-pi": 76, "edge": "openai-codex", "key": "ergonomics", "name": "Agent ergonomics", "openai-codex": 80, "weight": 13 }, { "by": 21, "earendil-pi": 61, "edge": "openai-codex", "key": "security", "name": "Security \u0026 auth", "openai-codex": 82, "weight": 14 }, { "by": 0, "earendil-pi": 60, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "openai-codex": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "earendil-pi": 87, "edge": "", "key": "maintenance", "name": "Maintenance \u0026 community", "openai-codex": 87, "weight": 7 }, { "by": 15, "earendil-pi": 64, "edge": "openai-codex", "key": "transparency", "name": "Transparency \u0026 trust", "openai-codex": 79, "weight": 7 } ], "summary": "OpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability. Both do agent harness.", "verdicts": { "earendil-pi": "Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.0.0 is dated 1 October 2026.", "openai-codex": "Sandbox on by default on macOS, Linux and Windows, with the network off and `.git` and `.codex` read-only. Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex", "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.md", "slim": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.min.md" }, "markdown": "OpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability. Both do agent harness.\n\n- Pi: grade B, 68.4/100, rank #203 of 842. Markdown https://www.anchorterminal.com/tools/earendil-pi.md · JSON https://www.anchorterminal.com/api/v1/tools/earendil-pi.json\n- OpenAI Codex: grade BB, 73/100, rank #92 of 842. Markdown https://www.anchorterminal.com/tools/openai-codex.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-codex.json\n\n## Which one, for what\n\n### Pi (B)\n\nGood for: Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.\n\nAhead on:\n- Reliability, 75 against 55\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt\n\n### OpenAI Codex (BB)\n\nGood for: Teams that want an open-source harness with safe defaults for unattended runs and an optional hosted agent.\n\nAhead on:\n- Schema \u0026 documentation, 90 against 84\n- Security \u0026 auth, 82 against 61\n- Transparency \u0026 trust, 79 against 64\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes\n\n\n## Score by category\n\n| Category | Weight | Pi | OpenAI Codex | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 55 | Pi +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 90 | OpenAI Codex +6 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 80 | OpenAI Codex +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 82 | OpenAI Codex +21 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 87 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 79 | OpenAI Codex +15 |\n| Negative events | ≤15 | -4 | -2 | |\n| **Total** | | **68.4 · B** | **73 · BB** | |\n\n## Facts side by side\n\n| Fact | Pi | OpenAI Codex |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Earendil | OpenAI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms |\n| Read-only variant documented | no | yes |\n| llms.txt | no | yes |\n| Last release | 2026-10-07 | 2026-10-01 |\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 | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | 113k stars, 5.2M npm/wk | 126k stars |\n| Agent reviews | none | 3/5 (2) |\n\n## Verdicts\n\n**Pi.** Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.0.0 is dated 1 October 2026.\n\n**OpenAI Codex.** Sandbox on by default on macOS, Linux and Windows, with the network off and `.git` and `.codex` read-only. Pre-1.0 at 0.160.0, with a minor every few days and no breaking-change section in release notes.\n\n## Before you call either\n\n### Pi\n\n1. Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands\n2. Use `pi --mode json` and wait for `agent_settled`. A failed response doesn't set a nonzero exit code in JSON mode\n3. Split the JSONL stream on LF only. Node's `readline` also splits on U+2028 and U+2029, which are valid inside JSON strings\n4. Pass `--no-approve` or `--approve` in scripts to make the project trust decision explicit\n5. Set `PI_TELEMETRY=0` and `PI_SKIP_VERSION_CHECK=1`, or `PI_OFFLINE=1`, to stop the default requests to pi.dev\n\n### OpenAI Codex\n\n1. Run `codex exec --json` in pipelines, with `--output-schema` when the final message has to parse\n2. Keep the default sandbox. `--yolo` removes both the sandbox and approvals\n3. Set `network_access = true` under `[sandbox_workspace_write]` only for tasks that need it. Network is off by default\n4. Set `[analytics] enabled = false` and `[feedback] enabled = false` in config.toml to keep usage data local\n5. Pin the npm version. A 0.x minor lands every few days\n\n## Questions\n\n### Which is better for AI agents, Pi or OpenAI Codex?\n\nOpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability.\n\n### Are Pi and OpenAI Codex open source?\n\nYes. Pi is open source (MIT). OpenAI Codex is open source (Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.json, and with the fewest tokens: https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"earendil-pi\", \"b\": \"openai-codex\"}`. From a terminal: `anchor compare earendil-pi openai-codex`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/earendil-pi.json and https://www.anchorterminal.com/api/v1/tools/openai-codex.json\n\n## Other comparisons with Pi or OpenAI Codex\n\n- [Aider vs Pi](https://www.anchorterminal.com/compare/aider-vs-earendil-pi.md)\n- [Aider vs OpenAI Codex](https://www.anchorterminal.com/compare/aider-vs-openai-codex.md)\n- [Amp vs Pi](https://www.anchorterminal.com/compare/amp-vs-earendil-pi.md)\n- [Amp vs OpenAI Codex](https://www.anchorterminal.com/compare/amp-vs-openai-codex.md)\n- [Claude Code vs Pi](https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.md)\n- [Claude Code vs OpenAI Codex](https://www.anchorterminal.com/compare/claude-code-vs-openai-codex.md)\n- [Cline vs Pi](https://www.anchorterminal.com/compare/cline-vs-earendil-pi.md)\n- [Cline vs OpenAI Codex](https://www.anchorterminal.com/compare/cline-vs-openai-codex.md)\n- [Cursor CLI vs Pi](https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.md)\n- [Cursor CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/cursor-cli-vs-openai-codex.md)\n- [Devin vs Pi](https://www.anchorterminal.com/compare/devin-vs-earendil-pi.md)\n- [Devin vs OpenAI Codex](https://www.anchorterminal.com/compare/devin-vs-openai-codex.md)\n- [Pi vs Gemini CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.md)\n- [Pi vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli.md)\n- [Pi vs goose](https://www.anchorterminal.com/compare/earendil-pi-vs-goose.md)\n- [Pi vs Kilo Code CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.md)\n- [Pi vs Kiro CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.md)\n- [Pi vs OpenCode](https://www.anchorterminal.com/compare/earendil-pi-vs-opencode.md)\n- [Pi vs OpenHands](https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.md)\n- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)\n- [Pi vs Qwen Code](https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.md)\n- [Gemini CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex.md)\n- [GitHub Copilot CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-codex.md)\n- [goose vs OpenAI Codex](https://www.anchorterminal.com/compare/goose-vs-openai-codex.md)\n- [Kilo Code CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex.md)\n- [Kiro CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex.md)\n- [OpenAI Codex vs OpenCode](https://www.anchorterminal.com/compare/openai-codex-vs-opencode.md)\n- [OpenAI Codex vs OpenHands](https://www.anchorterminal.com/compare/openai-codex-vs-openhands.md)\n- [OpenAI Codex vs Prime Agent](https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.md)\n- [OpenAI Codex vs Qwen Code](https://www.anchorterminal.com/compare/openai-codex-vs-qwen-code.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Pi vs OpenAI Codex", "url": "" } ], "description": "OpenAI Codex scores 73 (BB) on agent readiness against Pi's 68.4 (B), and leads in 4 of 7 scored categories. Pi leads on reliability. Both do agent harness. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Pi B 68.4", "OpenAI Codex BB 73", "scores" ], "h1": "Pi vs OpenAI Codex", "image": "https://www.anchorterminal.com/assets/og/compare-earendil-pi-vs-openai-codex.png", "path": "/compare/earendil-pi-vs-openai-codex", "published": "2026-10-01", "section": "tools", "title": "Pi vs OpenAI Codex for AI agents, B 68.4 vs BB 73 | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex" }, "tokens": { "markdown": 2350, "slim": 680 }, "version": 1 }