AI & Agents MCP servers

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor

Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.

Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.

Atom-grounded negotiation reasoning. Typed topology slot, inline citations, public dialect.

Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.

Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.

Authority-weighted memory graph for AI agents with conflict detection and semantic search.

Local-first AI context and memory server for cross-tool coding continuity.

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

MCP server providing access to 300+ AI models via OpenRouter

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

Bounded working memory for coding agents — typed nodes, current-vs-stale state, MCP-mountable.

Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.

Agent tracing, cost tracking, anomaly detection for LLM agents

MCP server exposing Minuet's ERC-8004 agent relationship graph.

Minimal stdio MCP server for parallel task execution by AI agents.

Local-first memory for coding agents; stores decisions, bugs, and context across sessions.

Wrap any CLI as a Model Context Protocol server - schema auto-inferred from --help.

Governed MCP workflows with policy validation, findings tracking, and review gates.

AI services via Bitcoin Lightning — PDF summarisation, code review, translation and more.

Local memory for Claude Code. Semantic recall across session history with zero API calls.

AI agent memory: task tracking, scoped work packages, decisions, and cross-session continuity

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

Let AI agents create configurable voice agents via meeting rooms and return structured data.

Aggregate multiple MCP backends behind a single stdio endpoint with namespaced routing.

The shared AI context engine for git — save, search, and share the reasoning behind code changes.