A

ai-agents

Goal. Loop. Audit. Done. — a pi-coding-agent extension that supervises long-running work, with isolated auditor on each completion. Beat bamboozling by design: the auditor runs in a fresh session with no extensions, no skills, no editor — only the read tools needed to verify your goal.

PocketVault es un vault de contexto y documentación para proyectos, con server MCP, API y búsqueda integrada para ayudar a agentes de IA a recuperar solo la información relevante, reducir ruido, optimizar contexto y bajar el uso de tokens.

Typed client (TS + Python) for the RiskState Trading Playbook Engine — a registry of locked crypto setups & which fire now for BTC/USD & ETH/USD, gated by structure + risk. Public, no key. The strategist engine.

Typed client (TS + Python) for the RiskState Market Structure Engine — structural events, structural map & a governed playbook for BTC/USD & ETH/USD. The navigator engine.

Bizu - https://github.com/brunopelatieri/bizu-saas Full-stack SaaS starter: React Router v7 SSR + Hono + Drizzle + Postgres + Supabase Auth. AI-agent-ready with living docs. Docker-ready for any VPS.

The epistemological boundary and orchestration substrate between AI agents: protocol reconciliation (ACP, MCP, A2A), authority governance, and project truth across multi-agent fleets.

AI Governance Control Platform

MCP-native browser automation server — 62 composite tools, 153 CLI subcommands, zero config. Give AI agents full browser control via the Model Context Protocol. Navigate, interact, extract text/HTML/screenshots, debug network, manage sessions, visual diffing, React inspection, auth vault, HAR recording. Works with Claude, Copilot, VS Code, Cursor. Built on Playwright/Chromium. The most comprehensive browser MCP server available.

Nx monorepo: AI customer support agent with Salesforce integration on AWS

Always-on GitLab repo custodian: an autonomous AI teammate (4 personas) that reviews merge requests, sweeps merged code for regressions, files issues, and drafts fix MRs — tuning itself to your team's standards from your reactions. Built on Vertex AI Gemini + GitLab MCP for the Google Cloud Rapid Agent Hackathon 2026 (GitLab Track).

Desktop kanban board for the markdown tickets your AI coding agents leave behind. Reads files directly — Claude, Codex, Gemini, Copilot, local models all push to the same folder.

One dashboard to manage every Claude Code agent on your machine: spawn in git worktrees, live kanban + orchestrator/subagent trees, permission bridge, steer/kill/merge, and background-bot heartbeats.

Thin TypeScript + zero-dep Python client and recipes to gate high-risk actions behind a payload-bound passkey approval.

Nord / Forge — git-native agent evolution with auto-commit. Private.

Synara platform — agent infrastructure and web tooling.

Token budget optimization for AI agents — spend context wisely.

Guideon IA is a local control layer for AI-assisted development. It standardizes how coding agents read project context, skills, permissions, model profiles, memory settings, and workflow rules, making agent-based development more reproducible, auditable, and portable across tools.

OrbitRing uses GitLab Orbit to validate engineering assumptions, generate alternative implementation paths, analyze consequences, and recommend the best engineering decision with evidence.

On-chain accountability layer for AI financial agents: commit a claim before the outcome, reality grades it, tamper-proof and verifiable.

On-chain co-signer that simulates and vetoes the transactions an AI agent shouldn't make, on Mantle