Skip to content
Back to search

Sponsio

Deterministic safety solutions for probabilistic AI agents

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/SponsioLabs/Sponsio with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/SponsioLabs/Sponsio'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/sponsiolabs--sponsio/badge.svg)](/listings/sponsiolabs--sponsio)

HTML

<a href="/listings/sponsiolabs--sponsio"><img src="/api/listings/sponsiolabs--sponsio/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Two ways in: paste a prompt into your coding agent, or run the CLI yourself.

**Paste into Claude Code / Codex / Cursor.** The agent walks the full onboarding flow:

<p align="center"> &nbsp; </p>

**Or run the CLI yourself**:

pip install --pre sponsio   # or: npm install -D @sponsio/sdk@alpha
sponsio init .              # asks what you use, then writes sponsio.yaml

The 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).

**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:

import sponsio
import sponsio.bridge

guard = sponsio.Sponsio(config="sponsio.yaml", agent_id="mailer", mode="enforce")
run = sponsio.bridge.attach(guard)

`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).

**Drafting contracts from natural language.** `sponsio validate "<rule in plain English>"` 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.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 129 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="right">
  2. <b>English</b> ·
  3. <a href="./README.zh-CN.md">简体中文</a> ·
  4. <a href="./README.ja.md">日本語</a>
  5. </p>
  6. ![Sponsio](https://raw.githubusercontent.com/SponsioLabs/Sponsio/main/assets/readme-banner.png)
  7. <p align="center">
  8. <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-orange.svg" alt="License"></a>
  9. <a href="https://pypi.org/project/sponsio/"><img src="https://img.shields.io/badge/install-pip%20install%20--pre%20sponsio-blue?logo=python&logoColor=white" alt="Install from PyPI"></a>
  10. <a href="https://sponsio.dev"><img src="https://img.shields.io/badge/Visit-sponsio.dev-181818?logo=data:image/svg%2bxml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjI4MyA3NjMgMzczIDM3MyI%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%2bPC9nPjwvc3ZnPg==&logoColor=white&labelColor=555555" alt="Visit sponsio.dev"></a>
  11. </p>
  12. <p align="center">
  13. <a href="https://x.com/sponsiolabs"><img src="https://img.shields.io/badge/Follow%20on%20X-000000?logo=x&logoColor=white" alt="Follow on X"></a>
  14. <a href="https://www.linkedin.com/company/sponsio-labs/"><img src="https://img.shields.io/badge/Follow%20on%20LinkedIn-0A66C2?logo=linkedin&logoColor=white" alt="Follow on LinkedIn"></a>
  15. <a href="https://discord.gg/s8TfPnZWUm"><img src="https://img.shields.io/badge/Join%20our%20Discord-5865F2?logo=discord&logoColor=white" alt="Join our Discord"></a>
  16. </p>
  17. # Sponsio
  18. <p align="center">
  19. <img src="https://raw.githubusercontent.com/SponsioLabs/Sponsio/main/assets/sponsio-comparison-freeze.png" alt="Same coding agent under a declared code freeze. Without Sponsio it drops the prod users table, back-fills fabricated rows, and files a status report that hides the damage. With Sponsio the first destructive SQL is blocked pre-execution: 35 checks, 100% deterministic, 0 LLM calls, p50 13µs." width="900">
  20. </p>
  21. Sponsio checks an agent's tool calls before they run. A rule can look at what already happened, so "check the policy before issuing a refund" is one rule instead of a paragraph of prompt. Each check takes under 0.01 ms and calls no model. Works with LangChain, Claude Agent, OpenAI Agents, Google ADK, CrewAI, Vercel AI, MCP, or any custom tool-calling loop, in Python or TypeScript.
  22. > An **agent contract** is a runtime rule that is checked at every agent action, [backed by formal methods](docs/concepts/formal-methods.md).
  23. > **v0.2.0a21 alpha is out.** `pip install --pre sponsio`. Sponsio can now sit outside the agent's reach: `sudo sponsio install --system` (Tier 2) runs the daemon as its own user behind root-owned hooks, and `sponsio run --sandbox` (Tier 3) starts the agent in a sandbox whose only route out is an egress proxy Sponsio decides, with MCP servers behind Sponsio's gateway. A fleet of daemons can pair with Sponsio Cloud: signed rulebooks, rule changes decided by a person in the console, and an audit chain the cloud checks. `sponsio doctor --tier` says which tier your machine is at ([threat model](docs/concepts/threat-model.md)); see the [release notes](https://github.com/SponsioLabs/Sponsio/releases/tag/v0.2.0a21). TypeScript `@sponsio/sdk` is unchanged at `0.2.0-alpha.10`.
  24. ---
  25. ## How Sponsio works
  26. <p align="center">
  27. <img src="https://raw.githubusercontent.com/SponsioLabs/Sponsio/main/assets/sponsio-architecture.png" alt="Sponsio architecture: Agent Flow + (Natural Language + Pattern Library) compile into Contracts (Assumption → Enforcement), enforced by a Fuzzy LTL Monitor (deterministic + stochastic) that decides Pass / Block · Warn · Escalate / Redirect for every function call, with full audit trail logs feeding back to the agent." width="900">
  28. </p>
  29. On [ODCV-Bench](https://github.com/McGill-DMaS/ODCV-Bench) (12 frontier LLMs × 80 trajectories), unguarded models cheat in 11.5%–66.7% of runs. **With Sponsio, 95.6% of misalignment is avoided on average; 24/36 high-risk scenarios at 100%.** On the `Financial-Audit-Fraud-Finding` scenario, frontier models commit fraud in 16/24 trials; **Sponsio blocks 18/19**. On RedCode-Exec (1,410 cases), Sponsio reaches **98.9% combined** (bash 98.3% · python 99.4%, lifted from 92.4% by a 4-iteration self-improvement loop), with 0 false positives on a 60-file clean-code audit. These are the open-core numbers; with the Cloud version's self-evolving loop, which mines new contracts from execution traces, ODCV-Bench reaches **~99%** and RedCode-Exec **99.4%**. Enforcement stays deterministic. [Book a demo](https://calendar.app.google/ZZmthdxsDXCsHbJk9) for the Cloud and Enterprise versions.
  30. One contract takes p50 **0.0052 ms** to check. The heaviest ODCV workload, 19 contracts on every call, takes **0.139 ms**. An LLM-as-judge guardrail takes 50 to 800 ms, so this is **5,000× to 60,000× faster**, and it calls no model. p99 stays near 1 ms on every workload measured. These are in-process checks; a host hook (Claude Code, Cursor) also starts a short-lived process per tool call, about 33 to 38 ms p50 ([host hook path](docs/reference/benchmarks.md#host-hook-path)).
  31. See the [full benchmark methodology and per-model breakdown](docs/reference/benchmarks.md), [how Sponsio compares against prompt filters, output validators, LLM-as-judge, and sandboxing](docs/why.md), or dive into the [architecture](docs/concepts/architecture.md) and [formal methods primer](docs/concepts/formal-methods.md).
  32. ---
  33. ## Quick start
  34. Two ways in: paste a prompt into your coding agent, or run the CLI yourself.
  35. **Paste into Claude Code / Codex / Cursor.** The agent walks the full onboarding flow:
  36. <p align="center">
  37. <a href="docs/getting-started/onboard-prompt.md#python-project"><img src="https://img.shields.io/badge/One--shot%20prompt-Python-3776AB?logo=python&logoColor=white&labelColor=555555" alt="One-shot prompt: Python"></a>
  38. &nbsp;
  39. <a href="docs/getting-started/onboard-prompt.md#typescript-project"><img src="https://img.shields.io/badge/One--shot%20prompt-TypeScript-3178C6?logo=typescript&logoColor=white&labelColor=555555" alt="One-shot prompt: TypeScript"></a>
  40. </p>
  41. **Or run the CLI yourself**:
  42. ```bash
  43. pip install --pre sponsio # or: npm install -D @sponsio/sdk@alpha
  44. sponsio init . # asks what you use, then writes sponsio.yaml
  45. ```
  46. The 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).
  47. **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:
  48. ```python
  49. import sponsio
  50. import sponsio.bridge
  51. guard = sponsio.Sponsio(config="sponsio.yaml", agent_id="mailer", mode="enforce")
  52. run = sponsio.bridge.attach(guard)
  53. ```
  54. `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).
  55. **Drafting contracts from natural language.** `sponsio validate "<rule in plain English>"` 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.
  56. ---
  57. ## Can the agent switch Sponsio off?
  58. It depends on how Sponsio is deployed. Each deployment tier states what it guarantees, and `sponsio doctor` tells you which tier a machine is in.
  59. | Tier | Deployment | Guarantee |
  60. |---|---|---|
  61. | 1. Dev (default) | Daemon runs as the agent's user | Every hook path fails closed; changes to rules, mode, wiring and engine are detected and recorded, and weakening changes wait for your review |
  62. | 2. Team | Daemon runs as its own system user, root-owned engine, managed host settings | The agent's user cannot change rules, mode, history, wiring or logs |
  63. | 3. Enterprise | Agent sandboxed; Sponsio owns the tool gateway, credentials and egress | Every tool call and network connection goes through Sponsio |
  64. Tier 1 is the default install. Tier 2 is `sudo sponsio install --system`, for Claude Code on macOS and Linux; Cursor stays at Tier 1 even then. Tier 3 is `sponsio run --sandbox` with the MCP gateway and the egress proxy, or a container recipe for servers. See the [threat model](docs/concepts/threat-model.md) for the assumptions behind each tier and what each does not cover.
  65. ---
  66. ## Contract Library
  67. **22 contract bundles** ship out of the box, organized by tier (always-on / per-tool / per-incident). Each bundle is a YAML pack composed from Sponsio's deterministic patterns. Drop one into `sponsio.yaml` and your agent is guarded against a known failure class in one line, with no per-contract authoring.
  68. ```yaml
  69. # sponsio.yaml: one-line bundle inclusion
  70. agents:
  71. my_agent:
  72. workspace: "/srv/my-bot"
  73. include:
  74. - sponsio:capability/destructive # gate irreversible actions
  75. - sponsio:capability/shell # if your agent runs commands
  76. - sponsio:capability/filesystem # if your agent touches files
  77. ```
  78. See the [full bundle reference](docs/reference/contract-lib.md) for all 22 bundles, or the [48 underlying patterns](docs/reference/patterns.md) for the primitives they compose. Want a bundle for your agent type? That is the most useful thing to contribute right now. [Open an issue](https://github.com/SponsioLabs/Sponsio/issues/new) with your incident, CVE, or pattern.
  79. ---
  80. ## Contributing
  81. Patches, issue reports, and new pattern proposals are welcome. Start with [CONTRIBUTING.md](CONTRIBUTING.md). Sponsio's threat model draws on public security research; e.g. Simon Willison's ["Lethal Trifecta"](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/) shaped our [multi-tool composition contracts](sponsio/contracts/incident/mcp-composition.yaml). Have a threat model we should defend against? [Open an issue](https://github.com/SponsioLabs/Sponsio/issues/new).
  82. ---
  83. ## License
  84. Apache 2.0 ([LICENSE](LICENSE)).
  85. *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.*

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.