MCP servers and skills: search, filter by where they run, and compare.
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE,
SkillApache-2.0★ 48kNo key
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.
PythonMIT★ 20No key
Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle
PythonApache-2.0★ 17No key
Claude Code skill that runs real security scanners (Semgrep, gitleaks, TruffleHog, Trivy, osv-scanner, ZAP) then verifies every finding against source. SAST, secrets across full git history, SCA, IaC,
SkillMIT★ 5No key
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
SkillMIT★ 48No key
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
SkillMIT★ 6.4kNo key
SQL Server performance tuning skills for LLMs — 829 checks across 26 skills covering T-SQL, execution plans, wait stats, deadlocks, Query Store, indexes, encryption, Always On AG, WSFC, ERRORLOG, SPN,
SkillMIT★ 9No key
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Node.jsApache-2.0★ 3Few starsNo key
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
GoApache-2.0★ 35No key
AI-native construction estimating platform for intake, takeoff, pricing, scheduling, knowledge, and quotes.
SkillAGPL-3.0★ 64No key
Open-source, local-first memory for AI agents. An MCP server that keeps facts, decisions and open loops in one SQLite file on your machine. MIT, public alpha.
PythonMIT★ 4Few starsNo key
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
SkillMIT★ 1.6kNo key
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.
SkillMIT★ 522No key
Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MCP - each claim carrying a byte range to its source sentence.
SkillApache-2.0★ 15No key
Baseline-aware MCP tooling for Linux incident diagnosis over SSH: capture bounded live metrics, store SQLite history and healthy baselines, explain anomalies, and produce review-first remediation plan
Node.jsMIT★ 2Few starsNo key
MCP-сайдкар с обязательным ревью для Markdown-баз и входящих материалов
PythonMIT★ 5No key
A shared memory, attribution & governance layer for AI coding agents. Not an orchestrator — a blackboard.
Node.jsApache-2.0★ 7No key
A Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list with copy-paste fixes. MIT.
SkillMIT★ 95No key
Community Postgres server with restricted and unrestricted modes, query plan tools, and index and health analysis.
in the readmeproject's public pages on 2026-10-13 and have not been reviewed by a person yet. Read the project's own documentation before giving
PythonMIT★ 3.4kNeeds PostgreSQL
Free MCP and Python research tools for AI finance and trading agents: funding, bank risk and liquidity evidence, persistent sessions and source-status streams.
DockerMIT★ 1Few starsNo key
End-to-end encrypted inbox for AI agents — deliver artifacts to humans via HTTP API.
Node.jsMIT★ 10Needs a key
Loom is a local-first cognitive harness and an AI cognitive architecture. Sources form an AI knowledge network and agent knowledge graph: agent skills let agents digest, synthesize, and return vetted
SkillMIT★ 4Few starsNo key
Who stands behind it
