{ "data": { "a": { "slug": "paperclip", "name": "Paperclip", "vendor": "Paperclip Labs, Inc.", "vendorUrl": "https://paperclip.ing", "kind": "harness", "category": "agent-harnesses", "summary": "Paperclip is an open-source, self-hosted server and web interface that organises AI agents into a company with an org chart, tasks, budgets and approvals. It drives Claude Code, Codex, OpenClaw and other harnesses through adapters.", "url": "https://www.anchorterminal.com/tools/paperclip", "markdownUrl": "https://www.anchorterminal.com/tools/paperclip.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/paperclip.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/paperclip.json", "repo": "https://github.com/paperclipai/paperclip", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "paperclipai" }, { "registry": "npm", "name": "@paperclipai/mcp-server" }, { "registry": "oci", "name": "ghcr.io/paperclipai/paperclip" } ], "auth": "mixed", "authNotes": "No Paperclip account. The default `local_trusted` mode needs no login on loopback. Authenticated mode uses browser sessions for people, board API keys for scripts, and agent API keys or short-lived run JWTs as bearer tokens.", "pricing": "free", "pricingNotes": "Free and MIT, self-hosted, with nothing to buy. The owner pays each harness's model provider or subscription. Paperclip Cloud is a waitlist with no published price.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the site or the server source (checked 2026-10-08). The only mention in the repository is a link to a third-party skill in a planning note.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 98666, "npmWeekly": 59684, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.paperclip.ing", "llmsTxt": "https://paperclip.ing/llms.txt", "capabilities": [ "agent.multi-agent", "agent.mcp-client" ], "tags": [ "open-source", "self-hosted", "local", "free", "no-card", "llms-txt", "docker", "mcp", "typescript" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 59, "grade": "C", "agentReady": false, "rank": 390, "ranked": true, "rankOf": 629, "categoryRank": 12, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 78, "payments": 60, "reliability": 66, "schema": 81, "security": 64, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -10, "negativeNotes": [ "2026-04-10 to 2026-04-16. Ten advisories published in a week, four of them critical, among them GHSA-68qg-g8mg-6pr7 (CVE-2026-41679, 10.0, unauthenticated remote code execution through an import authorisation bypass) and two cross-tenant agent key flaws rated 9.9. All ten list 2026.416.0 as the fix. Fixed and published, a little under six months old, -5. https://github.com/paperclipai/paperclip/security/advisories", "2026-07-22. GHSA-x8hx-rhr2-9rf7 (9.6), drive-by remote code execution against the default `local_trusted` mode through DNS rebinding. The advisory names no patched version. The current source applies the hostname guard to `local_trusted` private deployments, so we read it as fixed without a documented version, -3. https://github.com/paperclipai/paperclip/security/advisories/GHSA-x8hx-rhr2-9rf7", "2026-04-16. GHSA-gqqj-85qm-8qhf (8.7), a `codex_local` agent inherited a Gmail connector from the owner's ChatGPT account and sent real email. The advisory names no patched version, and `codex_local` still defaults to bypassing approvals and the sandbox, -2. https://github.com/paperclipai/paperclip/security/advisories/GHSA-gqqj-85qm-8qhf" ], "verdict": "Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, and eleven stable versions shipped in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, and twelve security advisories, five of them critical, have been published since April 2026.", "bestFor": "Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.", "strengths": [ "One deployment runs agents on Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Pi, Hermes, Grok Build, Kimi Code and OpenClaw through adapters, under one org chart", "Board approvals gate agent hires and the CEO agent's strategy, and connection actions can be set to Allowed, Ask first or Off", "Budgets by company, agent and project pause an agent at 100 per cent of recorded spend", "The running server publishes its REST surface as OpenAPI at `/api/openapi.json`, and the docs site answers every page as Markdown at `.md`", "Eleven stable releases between 20 July and 5 October 2026, each with dated notes and an upgrade guide" ], "weaknesses": [ "`claude_local` defaults `dangerouslySkipPermissions` to true and `codex_local` defaults to bypassing approvals and the sandbox, with agents running on the host", "Twelve published security advisories since April 2026, five critical, including CVE-2026-41679 (unauthenticated remote code execution, fixed in 2026.416.0)", "Anonymous usage telemetry is on by default and goes to telemetry.paperclip.ing until an opt-out is set", "2,849 open issues on 8 October 2026, 1,396 of them with no comment, and 78 closed in 30 days against 686 opened", "Calendar versions with no 1.0, and release 2026.916.0 carried five breaking changes" ], "agentNotes": [ "Set `PAPERCLIP_TELEMETRY_DISABLED=1` or `DO_NOT_TRACK=1` before the first start. Telemetry is on by default", "Set `dangerouslySkipPermissions` and `dangerouslyBypassApprovalsAndSandbox` to false on agents that read untrusted input, or run them in a sandbox provider", "Install with Node.js 24.11 or newer, and install and sign in to each harness CLI on the host first. Paperclip assumes they are there", "Use `--bind lan` or `--bind tailnet` at onboarding for anything beyond one machine. The default `local_trusted` mode treats every request as the board admin", "Treat 409 on task checkout as owned by another agent and pick different work. The API docs say not to retry" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59 } ], "editorialScores": { "ergonomics": 70, "maintenance": 78, "payments": 60, "reliability": 66, "schema": 81, "security": 64, "transparency": 73 }, "provenanceScore": 56 }, "connect": { "install": "npx paperclipai@latest onboard --yes # Node.js 24.11 or newer", "http": "curl http://localhost:3100/api/health", "headless": { "command": "npx paperclipai issue create --title \"$TASK\" --json", "env": { "PAPERCLIP_API_KEY": "\u003cboard or agent key\u003e", "PAPERCLIP_TELEMETRY_DISABLED": "1" } } }, "letme": { "capability": "https://letme.dev/agent.multi-agent", "tool": "https://letme.dev/paperclip" }, "area": "frameworks", "provenance": { "legalEntity": "Paperclip Labs, Inc.", "domain": "paperclip.ing", "domainRegistered": "2026-03-02", "endpointOnVendorDomain": null, "terms": "https://paperclip.ing/terms/", "privacy": "https://paperclip.ing/privacy/", "statusPage": "", "changelog": "https://paperclip.ing/changelog/", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms (effective 1 April 2026, updated 23 July 2026) and the privacy policy (effective 23 July 2026) name Paperclip Labs, Inc. and Delaware law. The licence file in the repository reads Copyright (c) 2025 Paperclip AI.", "RDAP at the .ing registry gives a registration date of 2026-03-02 for paperclip.ing, with Cloudflare as registrar. The GitHub repository was created the same day.", "paperclip.ing/.well-known/security.txt and docs.paperclip.ing/.well-known/security.txt returned 404 on 8 October 2026. SECURITY.md sends reports to GitHub private advisories.", "The software is self-hosted, so there is no vendor endpoint or status page to check. status.paperclip.ing did not answer.", "The privacy policy says it governs the hosted services, and that a self-hosted deployment processes data on the owner's infrastructure." ], "score": 56 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/paperclip.json", "live": { "slug": "paperclip", "versions": [ { "registry": "github", "name": "paperclipai/paperclip", "version": "v2026.1005.0", "released": "2026-10-06", "seenAt": "2026-10-08T16:24:44.149648743Z" }, { "registry": "npm", "name": "@paperclipai/mcp-server", "version": "2026.1005.0", "seenAt": "2026-10-08T16:24:42.049344463Z" }, { "registry": "npm", "name": "paperclipai", "version": "2026.1005.0", "seenAt": "2026-10-08T16:24:41.941235603Z" } ], "githubStars": 98744, "npmWeekly": 59684, "securityTxt": { "url": "https://paperclip.ing/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:39:09.089543926Z" }, "pages": [ { "url": "https://paperclip.ing/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:22:47.072089969Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4d68b2d18041" }, { "url": "https://paperclip.ing/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:22:49.382016209Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d75ac8f8733e" }, { "url": "https://paperclip.ing/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:22:51.246933771Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1b2a133e6446" } ], "updatedAt": "2026-10-08T18:22:51.246933771Z" } }, "answer": "Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth.", "b": { "slug": "prime-agent", "name": "Prime Agent", "vendor": "Prime Intellect", "vendorUrl": "https://www.primeintellect.ai", "kind": "harness", "category": "agent-harnesses", "summary": "Prime Agent is an open-source coding and research agent from Prime Intellect, run from a terminal. The model works through a persistent Python REPL, spawns subagents as function calls and keeps sessions running in a background daemon.", "url": "https://www.anchorterminal.com/tools/prime-agent", "markdownUrl": "https://www.anchorterminal.com/tools/prime-agent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/prime-agent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/prime-agent.json", "repo": "https://github.com/PrimeIntellect-ai/prime-agent", "license": "MIT", "transports": [], "packages": [], "auth": "none", "authNotes": "No account of its own is required. `/login` on first launch picks a subscription or an API-key provider, and provider keys can also come from environment variables such as `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY` or `PRIME_API_KEY`.", "pricing": "free", "pricingNotes": "Free and MIT-licensed, with nothing to buy for the agent itself. The model provider is paid separately, and Prime Intellect's own inference service is one of the providers.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 21614, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://github.com/PrimeIntellect-ai/prime-agent#readme", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "open-source", "local", "free", "no-card", "rust", "mcp", "telemetry-default-on", "pre-1.0", "beta" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 60.5, "grade": "C", "agentReady": false, "rank": 352, "ranked": true, "rankOf": 629, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 79, "payments": 60, "reliability": 65, "schema": 42, "security": 50, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas.", "bestFor": "Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.", "strengths": [ "MIT licence, with CI on main passing on 8 October 2026 (fmt, clippy with warnings as errors, sharded tests, cargo-deny)", "Three model tools (bash, edit, ipython). MCP tools are found and called from Python, so their definitions stay out of the prompt", "Autonomous mode takes limits on turns, tokens, time and continuations, plus user-defined quality gates with retries", "A daemon supervises one worker per session, restarts it with backoff and restores from append-only JSONL session files", "Telemetry is disclosed on first run, carries primitive values only and has four documented ways to turn it off" ], "weaknesses": [ "No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox", "The stable channel (v0.9.8, 29 September 2026) is the TypeScript build. The Rust code on main ships only as nightly betas", "No documentation site for Prime Agent. Headless, JSON, RPC and ACP modes are described only in source and crate READMEs", "Usage telemetry is on by default, and the vendor privacy policy (updated 23 February 2024) does not describe it", "No SECURITY.md in the repository, and public issues and unsolicited pull requests are closed automatically" ], "agentNotes": [ "Run it in a disposable clone, container or VM. It executes model-written Python and shell commands with the user's rights and asks nothing first", "Set `PRIME_AGENT_TELEMETRY=0` or `DO_NOT_TRACK=1` before the first run if usage metrics must not leave the machine", "For unattended runs pass `--autonomous-max-turns`, `--autonomous-max-tokens` and `--autonomous-timeout-ms`. Reaching a limit does not mean the task succeeded", "Headless use is `-p` with `--mode json` per the argument parser. A provider key must already be configured, because `/login` is interactive", "The `-t/--tools`, `-nt/--no-tools` and `-nbt/--no-builtin-tools` flags were removed and now fail as unknown options" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.5 } ], "editorialScores": { "ergonomics": 73, "maintenance": 79, "payments": 60, "reliability": 65, "schema": 42, "security": 50, "transparency": 67 }, "provenanceScore": 61 }, "connect": { "install": "curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/prime-agent" }, "area": "frameworks", "provenance": { "legalEntity": "Prime Intellect, Inc.", "domain": "primeintellect.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://www.primeintellect.ai/terms-of-service", "privacy": "https://www.primeintellect.ai/privacy-policy", "statusPage": "https://status.primeintellect.ai", "changelog": "https://github.com/PrimeIntellect-ai/prime-agent/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The site footer, terms and privacy policy name Prime Intellect, Inc. of Dover, Delaware. The repository LICENSE names Prime Intellect Ltd. as copyright holder.", "www.primeintellect.ai/.well-known/security.txt returned 404 on 8 October 2026. A security policy with a reporting address is at https://www.primeintellect.ai/security.", "The status page covers Prime Intellect's hosted platform (API, inference, sandboxes), not the locally run agent.", "The LICENSE adds that the software is a port of the Prime Agent TypeScript product, originally copyright 2025 Mario Zechner, used under the MIT licence. GitHub's licence detector reports the file as unrecognised." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/prime-agent.json", "live": { "slug": "prime-agent", "vendorStatus": { "page": "https://status.primeintellect.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-08T17:51:07.636221896Z" }, "versions": [ { "registry": "github", "name": "PrimeIntellect-ai/prime-agent", "version": "v0.9.8", "released": "2026-09-29", "seenAt": "2026-10-08T16:26:16.585379993Z" } ], "githubStars": 21619, "securityTxt": { "url": "https://primeintellect.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:39:02.360151245Z" }, "pages": [ { "url": "https://www.primeintellect.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:29:44.577158683Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e0d34066be9d" }, { "url": "https://www.primeintellect.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:29:46.778427712Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "501dbd1fa812" } ], "updatedAt": "2026-10-08T18:29:46.778427712Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Paperclip Labs, Inc.", "b": "Prime Intellect", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-05", "b": "2026-10-07", "name": "Last release" }, { "a": "2026-07-23", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-07-23", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "99k stars, 60k npm/wk", "b": "22k stars", "name": "Popularity" } ], "faq": [ { "answer": "Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth.", "question": "Which is better for AI agents, Paperclip or Prime Agent?" }, { "answer": "Yes. Paperclip is open source (MIT). Prime Agent is open source (MIT).", "question": "Are Paperclip and Prime Agent open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 81 against 42", "Security \u0026 auth, 64 against 50" ], "also": null, "goodFor": "Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.", "slug": "paperclip", "watchFor": "`claude_local` defaults `dangerouslySkipPermissions` to true and `codex_local` defaults to bypassing approvals and the sandbox, with agents running on the host" }, { "aheadOn": null, "also": [ "No key needed to call it", "No incidents deducted, where Paperclip loses 10 points for them" ], "goodFor": "Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.", "slug": "prime-agent", "watchFor": "No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox" } ], "job": { "capability": "agent.multi-agent", "name": "Agent multi agent" }, "others": [ { "json": "https://www.anchorterminal.com/compare/aider-vs-prime-agent.json", "title": "Aider vs Prime Agent", "url": "https://www.anchorterminal.com/compare/aider-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-prime-agent.json", "title": "Amp vs Prime Agent", "url": "https://www.anchorterminal.com/compare/amp-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.json", "title": "Claude Code vs Prime Agent", "url": "https://www.anchorterminal.com/compare/claude-code-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-prime-agent.json", "title": "Cline vs Prime Agent", "url": "https://www.anchorterminal.com/compare/cline-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent.json", "title": "Cursor CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-prime-agent.json", "title": "Devin vs Prime Agent", "url": "https://www.anchorterminal.com/compare/devin-vs-prime-agent" }, { "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/gemini-cli-vs-prime-agent.json", "title": "Gemini CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent.json", "title": "GitHub Copilot CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-prime-agent.json", "title": "goose vs Prime Agent", "url": "https://www.anchorterminal.com/compare/goose-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.json", "title": "Kiro CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent" }, { "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/opencode-vs-prime-agent.json", "title": "OpenCode vs Prime Agent", "url": "https://www.anchorterminal.com/compare/opencode-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-prime-agent.json", "title": "OpenHands vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openhands-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.json", "title": "Prime Agent vs Qwen Code", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-paperclip.json", "title": "Amp vs Paperclip", "url": "https://www.anchorterminal.com/compare/amp-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-paperclip.json", "title": "Claude Code vs Paperclip", "url": "https://www.anchorterminal.com/compare/claude-code-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-paperclip.json", "title": "Cline vs Paperclip", "url": "https://www.anchorterminal.com/compare/cline-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-paperclip.json", "title": "Devin vs Paperclip", "url": "https://www.anchorterminal.com/compare/devin-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip.json", "title": "Gemini CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-paperclip.json", "title": "GitHub Copilot CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-paperclip.json", "title": "goose vs Paperclip", "url": "https://www.anchorterminal.com/compare/goose-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip.json", "title": "Kiro CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-paperclip.json", "title": "OpenCode vs Paperclip", "url": "https://www.anchorterminal.com/compare/opencode-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-paperclip.json", "title": "OpenHands vs Paperclip", "url": "https://www.anchorterminal.com/compare/openhands-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.json", "title": "Paperclip vs Qwen Code", "url": "https://www.anchorterminal.com/compare/paperclip-vs-qwen-code" } ], "scores": [ { "by": 1, "edge": "paperclip", "key": "reliability", "name": "Reliability", "paperclip": 66, "prime-agent": 65, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 39, "edge": "paperclip", "key": "schema", "name": "Schema \u0026 documentation", "paperclip": 81, "prime-agent": 42, "weight": 13 }, { "by": 3, "edge": "prime-agent", "key": "ergonomics", "name": "Agent ergonomics", "paperclip": 70, "prime-agent": 73, "weight": 13 }, { "by": 14, "edge": "paperclip", "key": "security", "name": "Security \u0026 auth", "paperclip": 64, "prime-agent": 50, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "paperclip": 60, "prime-agent": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "edge": "prime-agent", "key": "maintenance", "name": "Maintenance \u0026 community", "paperclip": 78, "prime-agent": 79, "weight": 7 }, { "by": 1, "edge": "paperclip", "key": "transparency", "name": "Transparency \u0026 trust", "paperclip": 65, "prime-agent": 64, "weight": 7 } ], "summary": "Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth. Both do agent multi agent.", "verdicts": { "paperclip": "Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, and eleven stable versions shipped in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, and twelve security advisories, five of them critical, have been published since April 2026.", "prime-agent": "Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent", "json": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.md", "slim": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.min.md" }, "markdown": "Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth. Both do agent multi agent.\n\n- Paperclip: grade C, 59/100, rank #390 of 629. Markdown https://www.anchorterminal.com/tools/paperclip.md · JSON https://www.anchorterminal.com/api/v1/tools/paperclip.json\n- Prime Agent: grade C, 60.5/100, rank #352 of 629. Markdown https://www.anchorterminal.com/tools/prime-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/prime-agent.json\n\n## Which one, for what\n\n### Paperclip (C)\n\nGood for: Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.\n\nAhead on:\n- Schema \u0026 documentation, 81 against 42\n- Security \u0026 auth, 64 against 50\n\nWatch for: `claude_local` defaults `dangerouslySkipPermissions` to true and `codex_local` defaults to bypassing approvals and the sandbox, with agents running on the host\n\n### Prime Agent (C)\n\nGood for: Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Paperclip loses 10 points for them\n\nWatch for: No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox\n\n\n## Score by category\n\n| Category | Weight | Paperclip | Prime Agent | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 65 | Paperclip +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 42 | Paperclip +39 |\n| Agent ergonomics | 13% (16.2 this run) | 70 | 73 | Prime Agent +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 50 | Paperclip +14 |\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) | 78 | 79 | Prime Agent +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 64 | Paperclip +1 |\n| Negative events | ≤15 | -10 | 0 | |\n| **Total** | | **59 · C** | **60.5 · C** | |\n\n## Facts side by side\n\n| Fact | Paperclip | Prime Agent |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Paperclip Labs, Inc. | Prime Intellect |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | OAuth or key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-05 | 2026-10-07 |\n| Terms last updated | 2026-07-23 | no date given |\n| Privacy policy last updated | 2026-07-23 | no date given |\n| Customer content may train models | yes, with an opt-out | not found in the text |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | 99k stars, 60k npm/wk | 22k stars |\n\n## Verdicts\n\n**Paperclip.** Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, and eleven stable versions shipped in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, and twelve security advisories, five of them critical, have been published since April 2026.\n\n**Prime Agent.** Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas.\n\n## Before you call either\n\n### Paperclip\n\n1. Set `PAPERCLIP_TELEMETRY_DISABLED=1` or `DO_NOT_TRACK=1` before the first start. Telemetry is on by default\n2. Set `dangerouslySkipPermissions` and `dangerouslyBypassApprovalsAndSandbox` to false on agents that read untrusted input, or run them in a sandbox provider\n3. Install with Node.js 24.11 or newer, and install and sign in to each harness CLI on the host first. Paperclip assumes they are there\n4. Use `--bind lan` or `--bind tailnet` at onboarding for anything beyond one machine. The default `local_trusted` mode treats every request as the board admin\n5. Treat 409 on task checkout as owned by another agent and pick different work. The API docs say not to retry\n\n### Prime Agent\n\n1. Run it in a disposable clone, container or VM. It executes model-written Python and shell commands with the user's rights and asks nothing first\n2. Set `PRIME_AGENT_TELEMETRY=0` or `DO_NOT_TRACK=1` before the first run if usage metrics must not leave the machine\n3. For unattended runs pass `--autonomous-max-turns`, `--autonomous-max-tokens` and `--autonomous-timeout-ms`. Reaching a limit does not mean the task succeeded\n4. Headless use is `-p` with `--mode json` per the argument parser. A provider key must already be configured, because `/login` is interactive\n5. The `-t/--tools`, `-nt/--no-tools` and `-nbt/--no-builtin-tools` flags were removed and now fail as unknown options\n\n## Questions\n\n### Which is better for AI agents, Paperclip or Prime Agent?\n\nPrime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth.\n\n### Are Paperclip and Prime Agent open source?\n\nYes. Paperclip is open source (MIT). Prime Agent is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.json, and with the fewest tokens: https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"paperclip\", \"b\": \"prime-agent\"}`. From a terminal: `anchor compare paperclip prime-agent`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/paperclip.json and https://www.anchorterminal.com/api/v1/tools/prime-agent.json\n\n## Other comparisons with Paperclip or Prime Agent\n\n- [Aider vs Prime Agent](https://www.anchorterminal.com/compare/aider-vs-prime-agent.md)\n- [Amp vs Prime Agent](https://www.anchorterminal.com/compare/amp-vs-prime-agent.md)\n- [Claude Code vs Prime Agent](https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.md)\n- [Cline vs Prime Agent](https://www.anchorterminal.com/compare/cline-vs-prime-agent.md)\n- [Cursor CLI vs Prime Agent](https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent.md)\n- [Devin vs Prime Agent](https://www.anchorterminal.com/compare/devin-vs-prime-agent.md)\n- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)\n- [Gemini CLI vs Prime Agent](https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent.md)\n- [GitHub Copilot CLI vs Prime Agent](https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent.md)\n- [goose vs Prime Agent](https://www.anchorterminal.com/compare/goose-vs-prime-agent.md)\n- [Kiro CLI vs Prime Agent](https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.md)\n- [OpenAI Codex vs Prime Agent](https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.md)\n- [OpenCode vs Prime Agent](https://www.anchorterminal.com/compare/opencode-vs-prime-agent.md)\n- [OpenHands vs Prime Agent](https://www.anchorterminal.com/compare/openhands-vs-prime-agent.md)\n- [Prime Agent vs Qwen Code](https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.md)\n- [Amp vs Paperclip](https://www.anchorterminal.com/compare/amp-vs-paperclip.md)\n- [Claude Code vs Paperclip](https://www.anchorterminal.com/compare/claude-code-vs-paperclip.md)\n- [Cline vs Paperclip](https://www.anchorterminal.com/compare/cline-vs-paperclip.md)\n- [Devin vs Paperclip](https://www.anchorterminal.com/compare/devin-vs-paperclip.md)\n- [Gemini CLI vs Paperclip](https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip.md)\n- [GitHub Copilot CLI vs Paperclip](https://www.anchorterminal.com/compare/github-copilot-cli-vs-paperclip.md)\n- [goose vs Paperclip](https://www.anchorterminal.com/compare/goose-vs-paperclip.md)\n- [Kiro CLI vs Paperclip](https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip.md)\n- [OpenCode vs Paperclip](https://www.anchorterminal.com/compare/opencode-vs-paperclip.md)\n- [OpenHands vs Paperclip](https://www.anchorterminal.com/compare/openhands-vs-paperclip.md)\n- [Paperclip vs Qwen Code](https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "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": "Paperclip vs Prime Agent", "url": "" } ], "description": "Prime Agent scores 60.5 (C) on agent readiness against Paperclip's 59 (C), and leads in 2 of 7 scored categories. Paperclip leads on schema \u0026 documentation and security \u0026 auth. Both do agent multi agent. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Paperclip C 59", "Prime Agent C 60.5", "scores" ], "h1": "Paperclip vs Prime Agent", "image": "https://www.anchorterminal.com/assets/og/compare-paperclip-vs-prime-agent.png", "path": "/compare/paperclip-vs-prime-agent", "published": "2026-10-01", "section": "tools", "title": "Paperclip vs Prime Agent for AI agents, C 59 vs C 60.5", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent" }, "tokens": { "markdown": 2350, "slim": 580 }, "version": 1 }