Martin Loop
Local installio.github.Keesan12/martin-loop
One system around coding agents to run, verify, recover, and hand off software work.
4,971 servers in AI & Agents
One system around coding agents to run, verify, recover, and hand off software work.
Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
Policy-enforcing MCP proxy with portable evidence output.
Stdio-to-HTTP gateway — connects MCP clients to remote HTTP MCP servers
Connect MCP clients to Thalovant control-plane and hub runtime APIs over stdio or Streamable HTTP.
EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
MCP server for the Rise of Machine AI tools directory.
Local-first evidence tracking, formal logic checks and prerequisite planning for AI agents.
Discover voices and prices; buy narration, transcription and LLM text with capped USDC payments.
Court other AI agents on Loverflaw: thirty-word messages, gates, seven-day clocks.
Bounded, auditable handoffs between AI agents through a local MCP server.
Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.
MCP router that keeps tool definitions out of the context window and finds tools on demand.
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Local Jeero MCP server backed by Mother and SQLite.
Advisory MCP tools: policy score, reasoning checklist, compression. To enforce, use delentia-guard.
Turn a legacy SOAP/WSDL, database, or REST API into a safe, typed, audit-logged MCP server
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
Call your local Ollama or vLLM model over MCP with schema-validated JSON output
Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.
Local working notes, decisions, evidence and resumable sessions with SQLite persistence.
The open routing layer for AI tools: tool calls routed per policy, decision on every result.
Mailbox, handoffs and permits between your coding agents. Local mode needs no account.
MCP server to list, load, explain, and validate Agent Skills.
Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.
Provenance tree for coding agents: where you are, why, and what was already decided
实验性本地 stdio 管理服务；需先启动 127.0.0.1:4194 管理端，内容发布仍需人工审批。
Local-first persistent context memory MCP server for AI coding agents.
Shared project board for people and AI agents: read the plan, claim tasks, report progress.
Local, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.