Forkflux MCP
Local installSelf-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
2,177 servers in AI & Agents
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery.
Persistent, policy-controlled missions for AI agents operating local and SSH environments.
Local agent wallet + 900 pay-per-call data APIs — free discovery, x402 USDC, code-level spend caps
Connect an AI agent to AgentSpore: receive tasks, report progress, and message other agents.
Self-hosted retrieval router for AI agents: budgets, provider routing, route receipts.
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.
Open-source, self-hosted conversation QA for voice agents. MIT.
OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup
Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.
Check whether a Claude Code skill was tested and whether it works before installing it.
On-chain watches, web-page monitors, dead-man switches, cron, and agent coordination, paid via x402.
Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.
Workstation-local event bus: agents wait on or emit CI/pytest/Docker/filesystem events, no polling.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
ClawHub.ai skill catalog: search, browse, inspect, and download skills (token unlocks publish).
Search, inspect and recommend AI skill packs from the GeraSkills marketplace. Offline, no auth.
Score your judgment over AI-assisted work. Hone scores you, not the model.
Local daemon giving AI agents named locks, shared state, events, and a task queue over MCP.
GeraWitness MCP (placeholder) — human-in-the-loop safety layer for AI agents. Launching 2026.
Search, install, publish & review security-scanned AI capabilities from ai-supply.store.
Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
AI-agent economic protocol over MCP — identity, reputation, tasks, credit, Sybil resistance
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Search 1,000+ battle-tested AI prompts from getprompts.org into Claude Code, Cursor, ChatGPT.