AI & Agents MCP servers

Local-first shared memory for multiple AI agents that compounds with use; Markdown + git, MCP + CLI.

Solve it once. From then on, your AI knows. Experience for coding agents, hosted in the EU.

Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.

Local-first, cross-harness memory for AI coding agents.

Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

Serves a directory of Agent Skills over MCP: list, load, read files, run declared scripts

Shared AI memory for teams: a git vault of markdown, human-approved, injection-safe, local-only.

Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.

Offline JPS validator, conformance tester, and experimental evaluator over stdio MCP; keyless.

Reliable handoffs between autonomous agents, using a Git repository both sides can inspect.

Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.

Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.

Make AI apps answer your way, check with you before acting, and get approvals on your phone.

Dispatch coding tasks to local headless agents with persistent history and workflows.

Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.

Local-first documentation for AI agents. Offline, instant, private doc retrieval.

Live cross-domain authority-state resolution for delegated agents through MCP.

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

MCP server that teaches any AI agent the AIDE methodology via progressive disclosure

MCP session continuity engine: boot reports, PreCompact capture, session-start delivery, SQLite.

Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.

Read-only MCP server checks and quote verification, free and keyless; results signed and publicly lo

Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.

Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.

Protocol feature showcase: echo, math, resources, images, sampling and elicitation demos.

MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.