A TypeScript CLI framework that ships your commands as a CLI, agent skills, and MCP.

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

A formal workflow protocol that keeps AI coding agents on track through machine-enforced invariants, verified evidence, and structured context. Designed to keep deep, long-running projects coherent across sessions, agents, and months.

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules

Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

Local-first memory and dreaming automation for agents.

Instant web hosting for AI agents. One curl, one CLI, *.wooven.dev URL in <1s.

Mission orchestrator and lab for local AI. Launch a mission, watch the graph come alive — every seat runs your own models off the meter, or a hosted endpoint.

A decision engine for Claude Code. MIT licensed.

Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across VS Code/Copilot, OpenCode, Cursor, Zed, Claude Code, and Pi.

Package manager and registry for Claude skill packages - install, validate, score, and publish .skill packages with Claude Code integration via MCP

A Claude Code plugin that gives Claude a self-introspection tool for its own subscription quota — so it can warn you before a long task runs out of budget.

Beautiful, informative status line for Claude Code. Zero dependencies, cross-platform. pip install claude-status

Deterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.

An agent friendly tool for converting images to SVG

Portable, inspectable knowledge bundles for LLM agents.