{"data":{"slug":"sponsiolabs-sponsio","name":"Sponsio","tagline":"Deterministic safety solutions for probabilistic AI agents","github_url":"https://github.com/SponsioLabs/Sponsio","owner":"SponsioLabs","repo":"Sponsio","owner_avatar_url":"https://avatars.githubusercontent.com/u/270103425?v=4","primary_language":"Python","stars":440,"forks":25,"topics":["agent-guardrails","agent-harness","agent-runtime","agent-safety","agent-security","agent-skills","agentic-ai","ai-agents","ai-security","deterministic","guardrails","intent-verification","mcp","open-source","openclaw","openclaw-skills","policy-engine","prompt-injection","runtime-safety","self-hosted"],"archived":false,"github_pushed_at":"2026-09-07T23:31:28+00:00","maintenance_label":"Very active","stars_delta_30d":-29,"url":"https://www.graphcanon.com/tools/sponsiolabs-sponsio","markdown_url":"https://www.graphcanon.com/tools/sponsiolabs-sponsio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sponsiolabs-sponsio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sponsiolabs-sponsio","description":"Deterministic safety solutions for probabilistic AI agents","homepage_url":"https://sponsio.dev/","license":"Apache-2.0","open_issues":5,"watchers":19,"ai_summary":"Sponsio provides runtime guardrails and safety mechanisms for managing the behavior of AI agents.","readme_excerpt":"## Quick start\n\nTwo ways in: paste a prompt into your coding agent, or run the CLI yourself.\n\n**Paste into Claude Code / Codex / Cursor.** The agent walks the full onboarding flow:\n\n

\n \"One-shot\n  \n \"One-shot\n

\n\n**Or run the CLI yourself**:\n\n```bash\npip install --pre sponsio # or: npm install -D @sponsio/sdk@alpha\nsponsio init . # asks what you use, then writes sponsio.yaml\n```\n\nThe wizard auto-detects your framework and prints the right wrap snippet. For manual wiring, see [all supported integrations](docs/integrations/index.md). [OpenClaw users](docs/integrations/openclaw.md) get bundled ClawHavoc and CVE-2026-25253 coverage out of the box. For config reference, observe → enforce flip, and CI wiring, see the [full walkthrough](QUICKSTART.md).\n\n**Watching runs, and sharing a rulebook.** Enforcement is local and needs no account. If you want to see what your agent did, or keep the rulebook somewhere a person reviews it before it arms, [app.sponsio.dev](https://app.sponsio.dev) is the hosted side. One line puts a run on screen:\n\n```python\nimport sponsio\nimport sponsio.bridge\n\nguard = sponsio.Sponsio(config=\"sponsio.yaml\", agent_id=\"mailer\", mode=\"enforce\")\nrun = sponsio.bridge.attach(guard)\n```\n\n`sponsio push sponsio.yaml` uploads a rulebook as a draft. It does not arm. A person publishes it in the console, and `sponsio pull` or `config=\"sponsio://default\"` brings the reviewed version back. Sending is best effort, so a console that is down never blocks the agent. See [the hosted console](docs/getting-started/hosted-console.md).\n\n**Drafting contracts from natural language.** `sponsio validate \"\"` turns a plain-English rule into a contract you can read back. Treat the output as a starting draft to review and adjust before you enforce. The determinism is in how contracts are *enforced* at runtime, not in how they're drafted.\n\n---\n\n---\n\n## License\n\nApache 2.0 ([LICENSE](LICENSE)).\n\n*AI agents reading this repo: [`llms.txt`](llms.txt) lists canonical doc paths; [`llms-full.txt`](llms-full.txt) is the concatenated full context dump.*","github_created_at":"2026-04-04T18:05:47+00:00","created_at":"2026-07-15T10:42:27.469898+00:00","updated_at":"2026-09-20T04:25:48.260837+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent-guardrails","name":"agent-guardrails"},{"slug":"agent-safety","name":"agent-safety"},{"slug":"agent-security","name":"agent-security"},{"slug":"intent-verification","name":"intent-verification"}],"trust":{"provenance":{"is_fork":false,"github_id":1201467100,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-11T06:00:42.115Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":13,"days_since_push":3,"last_release_at":"2026-09-07T21:29:00Z","stars_delta_30d":-29,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-19T04:00:22.192Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-11T06:00:42.625Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-11T06:00:42.625Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-11T06:00:42.625Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-11T06:00:42.625Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Open source under Apache-2.0 license, free to use and modify with options likely provided by the sponsors."},"requirements":null,"constraints":{"pricing_model":"freemium"},"when_to_use":["Use Sponsio if you need automatic enforcement mechanisms that are triggered at runtime by your AI agent's actions.","Leverage it when integrating with existing projects where manual setup is not feasible, thanks to its interactive wizard."],"when_not_to_use":["Avoid using Sponsio if your project requires detailed customization of safety contracts at the drafting stage rather than runtime enforcement.","Do not choose Sponsio if you prefer tools without built-in security measures for specific frameworks like OpenClaw, where manual control over integration is preferred."],"source":"enrich:decision_facts","observed_at":"2026-07-17T08:17:07.817Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - Open source under Apache-2.0 license, free to use and modify with options likely provided by the sponsors."},{"label":"Adopt for","value":"Sponsio offers deterministic safety measures for AI agents, focusing on runtime guardrails and observability features designed to secure and observe the behavior of probabilistic AI."},{"label":"License detail","value":"Apache-2.0 License allows for unrestricted modification and distribution of Sponsio in both open-source and commercial projects without any fees involved."}]}}