AI & Agents MCP servers

Focused, production-ready CLI: turn any OpenAPI REST API into an MCP server.

Session memory for AI coding agents: records decisions and dead ends, flags what went stale.

Agent memory where every fact carries a receipt, and deletion is provable.

Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

A lightweight, Git-backed permanent memory for AI agents.

Local-first persistent memory for coding agents and MCP clients.

Search evidence-labelled MCP servers with freshness, install, compatibility and verification data.

Local-first RAG engine with MCP server for AI agent integration.

Local MCP control plane for persistent sessions and compact capability discovery.

Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.

Local-first durable AI memory with policy-bound recall and a typed project graph.

Git module dependencies and owning-agent routing for coding agents

Zero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.

Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.

Read-only local progress, usage, lock state, work lists, and verified run receipts.

Durable local-first MCP relay for independent coding agents.

Kanban do Intelliboard por MCP: handoff entre agentes e validação imposta antes de concluir.

Deterministic logical reasoning engine — facts in Euclid IR, solutions with proof trees

Expose declarative YAML-defined workflows as MCP tools over stdio

AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.

Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.

Persistent code memory for AI agents: notes pinned to files and symbols that survive refactors.

Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.

Per-call paid skills for AI agents, run server-side: inputs in, outputs back. The body never ships.

Test whether AI agents retain critical instructions as conversations grow.

Local chronological memory banks you control; Claude recalls them via MCP.

Screen AI-work venues for inventory, funding, payouts, withdrawal, economics, and security risk.

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.