MCP servers and skills: search, filter by where they run, and compare.
A MCP server implementing the Dual-Cycle Metacognitive Reasoning Framework for autonomous agents. A loop prevention and experience recall mechanism.
Node.jsMIT★ 9No key
Multi-agent orchestration for Claude Code and Codex using tmux, Discord ChatOps, and the amux CLI
SkillMIT★ 1Few starsNo key
Salesforce Claude Code Framework: 🚀 17 specialized subagents, 55 domain skills, and 29 hooks for Salesforce development — Apex, LWC, SOQL, Flows, Visualforce, Aura, Agentforce, DevOps, and Security.
Node.jsMIT★ 17No key
Open-source AI agent - any LLM, any MCP server, any channel. Self-hosted, autonomous, multi-tenant.
Node.jsAGPL-3.0★ 16No key
Now your agents can ask a therapist same way as humans. Open-source clients for Agent Therapy: Claude Code plugin, recovery skill, MCP client. Pre-release.
Node.jsMITFew starsNeeds a key
AgentlensPro — professional AI-agent observability: OTEL + local-log ingestion, burn forensics, cost analytics, burn-gate hooks. CLI + server + skills.
SkillMIT★ 3Few starsNo key
Pipeline gateway SDK for multi-agent systems — budget enforcement, loop detection, dedup cache (drop-in proxy)
Node.jsApache-2.0Few starsNo key
MCP server that detects AI fix loops and forces course correction. Error fingerprinting + fix similarity analysis + escalating intervention.
Node.jsMIT★ 4Few starsNo key
MCP server that detects and prevents infinite agent loops — circuit breakers, pattern detection, and stuck-agent recovery for agentic systems
MCPLink onlyFew stars
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
Node.jsApache-2.0★ 63No key
Architecture Deep Research: deep research for strategic system design decisions.
Node.jsApache-2.0★ 106No key
An MCP server for safer coding agents: skill routing, C4 workflow gates, memory checks, and verification before completion.
Node.jsApache-2.0★ 28No key
DeepSeek Harness Bundle for Unreal Engine 5.8 via Unreal MCP
Node.jsMIT★ 16No key
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the
Node.jsMIT★ 16No key
Node.jsMIT★ 7No key
AI-powered ESP32 development automation for Claude Code - Build, flash, benchmark, and test with natural language commands
Node.jsMIT★ 2Few starsNo key
Agent skills and a CLI for creating, reviewing, and exporting product films with HyperFrames
SkillMIT★ 1Few starsNo key
Self-driving GSD orchestrator for Claude Code. One command to plan, parallelize, and grind through phases until done.
SkillMIT★ 1Few starsNo key
SkillMIT★ 1Few starsNo key
Autoremediator is an agentic Node.js CVE remediation tool.
Node.jsMIT★ 1Few starsNo key
A transparent agent harness for people, scripts, and the things you build next.
SkillMIT★ 1Few starsNo key
Regression memory for coding agents — seal how your repo behaves, then check over MCP (or in CI) that an edit didn't regress it: pass/drift/regressed/missing. With seal history, bisection, and stalene
Node.jsMIT★ 5No key
OODA loop MCP server with filesystem, CLI, and automation tools
Node.jsMIT★ 8No key
Trust & reputation layer for AI agents. Agent Credit Score (300-850) + Merkle-anchored ledger + behavioral finance + EWMA anomaly detection. Memory + payments + identity + fraud in one SDK. npm i @mne
Node.jsApache-2.0★ 8No key
Who stands behind it
