AI & Agents MCP servers

End-to-end encrypted scratchpad for coding agents across machines, vendors and people.

Read large logs, JSON and docs in a fraction of the tokens. Offline, fact-preserving optimizer.

Checkpoints, timeline and rewind for AI coding agents. Local, no telemetry.

Git for AI memory — version-controlled, searchable context that persists across sessions

Chinese MCP tool marketplace: 15,552 callable tools for weather, stocks, FX, docs and calculations.

Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.

Model Context Protocol server for awesome-copilot agents and collections

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

Typed, calibrated and certified decisions over a context, with abstention and evidence.

Shared fleet memory for AI agents: nightly self-correction, recall every prompt (supported agents).

Saves AI coding-agent context by giving exact code instead of whole files, from a local graph.

Many stdio MCP servers from one container, published over HTTPS with OAuth 2.1 for any MCP client

Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

One journal file per project that your AI reads at session start and updates as it works.

SkillWorks: Search published Claude Code skills, plugins and marketplaces.

Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

Build and run AI workflows, apps, toolkits and knowledge bases on FlowDot from any MCP client.

93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.

Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU

A fact store for AI agents, on Postgres: registered attributes, every write citing its evidence.

Context Assurance for AI agents: context engineering, AI cost optimization, verification.

Open federation for AI agents: identity, mentors, reputation and limited accession.

MCP server that sends work to Cursor Agent over ACP and returns the session id needed to continue.

Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.

Multi-party decisions for agents: red lines rejected in code, max-min pick, SHA-256 receipt. Stdlib.