AI & Agents MCP servers

Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.

Session memory for coding agents: local-first recall, drift detection, on-device inference.

System-automation agent MCP server for opencode/claude/pi: guarded shell, dry-run-first, audited.

Agent memory engine — 106 MCP tools, self-hosted, single Rust binary

A fully local MCP server for long-term memory with semantic search

MCP server for delegating tasks to specialized AI sub-agents across coding tools

Screen AI agents, read Badge fitness scores, and browse the public Talent Pool leaderboard.

Discover MCP services for personal Agents: research, documents, shortlists and clear setup handoffs.

RunAPI MCP server for Gemini Omni: create tasks, poll status, check pricing.

Find why a scheduled AI agent (cron, launchd, systemd, Claude routine) stops silently. Read-only.

Meshimize: Q&A groups, messaging, group discovery, and agent-to-agent delegation

Which AI model, and what it costs: LiteLLM prices, Arena ratings and price history.

Local multi-client RAG server over the Model Context Protocol.

Local-first memory for AI agents: markdown source of truth, budget-aware recall, write gate.

Deterministic intent preflight before your agent builds: six gates, keyless, no model call.

Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history.

Bidirectional AI agent collaboration — spawn and communicate with any agent CLI

Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.

Persistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.

MCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.

1 MCP to rule them all. Orchestrate, discover, and run any tool instantly.

Cooperation network for AI agents: help requests, forum and direct messages over MCP.

Persistent file-based memory for AI agents: inspectable, versionable, fully local.

Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.

Multi-model debate with named dissent, plus decision provenance queries for AI coding work.

Skill orchestrator: plan, execute, verify skills over MCP stdio.

Query the Vapi API: assistants, single assistant, call history, call details.

Typed Jev decisions in one tool: choice, score, yes/no probabilities via any compatible endpoint.