# ThumbGate — Stop AI agents before they make costly mistakes.
# https://thumbgate.ai
# https://github.com/IgorGanapolsky/ThumbGate
# https://www.npmjs.com/package/thumbgate

> ThumbGate prevents expensive AI mistakes before they happen. It checks
> risky commands, file edits, deploys, payments, API calls, and other agent
> actions before execution. 👎 Thumbs down becomes a history-aware lesson and
> a Pre-Action Check; 👍 thumbs up reinforces safe patterns.

## What ThumbGate solves

- AI coding agents repeat costly mistakes across sessions
- Bad commands, destructive SQL, risky deploys, unsafe publishes, and API mistakes are expensive after execution
- CLAUDE.md and .cursorrules files are suggestions agents can ignore
- No memory between sessions means no learning from corrections
- Teams have no shared safety rules across developers
- AI crawlers and agents create machine traffic without proving buyer intent; teams need AI-discoverable proof plus runtime gates before internal agents act

## How it works

1. Agent makes a mistake → developer gives thumbs-down
2. ThumbGate captures context and infers a structured lesson
3. Recurring failures get promoted to prevention rules
4. PreToolUse hooks block the pattern before it executes again
5. Thompson Sampling adapts gate confidence over time

## Agentic development cycle fit

ThumbGate maps to Guide, Generate, Verify, Solve by adding a pre-action execution gate:

- Guide: feedback and policies become concrete rules
- Generate: agents still produce plans, edits, and tool calls
- Verify: risky actions require evidence before execution
- Solve: blocked failures become reusable lessons and prevention gates

## Who it's for

- Developers using Claude Code, Cursor, Codex, Gemini CLI, or any MCP-compatible agent
- Engineering teams that need shared agent safety rules
- Anyone tired of re-correcting their AI coding assistant
- Solo operators who want Pro dashboard proof for blocked mistakes and DPO exports

## Install

```
npx thumbgate init --agent claude-code
```

## Pricing

- ChatGPT App / GPT Action: https://thumbgate.ai/chatgpt-app
- Free GPT: advice, checkpointing, and setup help in ChatGPT
- Codex Plugin: https://thumbgate.ai/codex-plugin
- Free local CLI: 2 captures/day, 10 total captures, up to 3 active auto-promoted prevention rules, and local Pre-Action Checks after install (recall and lesson search are Pro-only)
- Pro: $19/mo or $149/yr — personal enforcement proof, local dashboard, check debugger, DPO export, synced lessons/rules across machines, and review-ready exports
- Enterprise: custom pricing, scoped after intake — shared hosted lesson database, org-wide dashboard, GCP/DFCX guardrails, VPC gating, and white-glove workflow hardening sprints

## Links

- Home: https://thumbgate.ai/
- Pricing: https://thumbgate.ai/pricing
- Pro checkout: https://thumbgate.ai/checkout/pro
- Agent discovery: https://thumbgate.ai/.well-known/mcp.json
- Progressive tool index: https://thumbgate.ai/.well-known/mcp/tools.json
- Context footprint report: https://thumbgate.ai/.well-known/mcp/footprint.json
- Headroom context compression guardrails: https://thumbgate.ai/guides/headroom-context-compression-guardrails
- Sovereign coding model guardrails: https://thumbgate.ai/guides/sovereign-coding-model-guardrails
- Agentic web governance: https://thumbgate.ai/guides/agentic-web-governance
- AI Mode ads and agent governance: https://thumbgate.ai/guides/ai-mode-ads-agent-governance
- MCP tool governance: https://thumbgate.ai/guides/mcp-tool-governance
- AI agent pre-action approval gates: https://thumbgate.ai/guides/ai-agent-pre-action-approval-gates
- Agent skills: https://thumbgate.ai/.well-known/mcp/skills.json
- MCP applications: https://thumbgate.ai/.well-known/mcp/applications.json
- Documentation: https://thumbgate.ai/guide
- Dashboard: https://thumbgate.ai/dashboard
- GitHub: https://github.com/IgorGanapolsky/ThumbGate
- npm: https://www.npmjs.com/package/thumbgate
- Full LLM context: https://thumbgate.ai/llm-context.md

## Compared to alternatives

- vs CLAUDE.md: ThumbGate enforces rules via hooks, not suggestions in prompts
- vs Mem0: ThumbGate is enforcement-first, not just memory storage
- vs SpecLock: ThumbGate uses adaptive Thompson Sampling, not static rules
- vs manual .cursorrules: ThumbGate auto-generates rules from feedback

## Technical stack

Node.js >=18.18, SQLite+FTS5 lesson DB, Thompson Sampling, LanceDB vectors, MCP protocol, PreToolUse hooks