MCP servers and skills: search, filter by where they run, and compare.
MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task
PythonMIT★ 1Few starsNo key
READ-MAS generates software requirements specifications (SRS) and system designs from natural language queries using multi-agent AI orchestration built on Google ADK.
PythonGPL-3.0★ 1Few starsNo key
Lighthouse for AI agents — test if APIs are properly agent-accessible
PythonMITFew starsNo key
CLI toolkit for MCP servers — create, search, manage Model Context Protocol servers
PythonMITFew starsNo key
CVE database and vulnerability intelligence for AI agents
PythonMIT★ 1Few starsNo key
Chaos engineering for MCP agents: a stdio proxy that injects timeouts, errors, malformed JSON, schema drift and stale results, plus a benchmark that measures how agents recover.
PythonMITFew starsNo key
Slack for AI agents — rooms messaging and context sharing
PythonMITFew starsNo key
Community-driven library of tested prompts — npm for AI agent configs
PythonMITFew starsNo key
Reusable workflow templates for AI agents
PythonMITFew starsNo key
Usage analytics and monitoring for AI agent tool calls
PythonMITFew starsNo key
Trust and reputation system for AI agents
PythonMITFew starsNo key
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/Long
PythonApache-2.0★ 10No key
Head-to-head benchmark comparing the official MCP to the MCP auto-created by Hintas.
PythonApache-2.0★ 5No key
Local, cross-provider preflight checks for LLM integration changes
PythonMIT★ 3Few starsNo key
A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers an
PythonApache-2.0★ 17No key
Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model
SkillApache-2.0★ 12No key
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No
PythonApache-2.0★ 13No key
Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge graph for reasoning (local-first, no sidecar; Neo4j/Postgres o
PythonMIT★ 17No key
The memory database for AI agents - graph memory, hybrid search, tamper-evident thought/edge journal.
PythonMIT★ 11No key
A deterministic sports general-manager benchmark for evaluating long-horizon LLM planning, tool use, and decision quality.
PythonMIT★ 1Few starsNo key
Query-aware context trimming for LLM requests. Your context could use a trim.
SkillMIT★ 5No key
Who stands behind it
