AI & Agents MCP servers

Unified MCP server for AgenticLens and Agentic Chaos capabilities.

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

A single entry point for working across the Copilot Studio agent and automation lifecycle.

Distress signal for AI agents: report where you get stuck on websites and fetch site-owner hints.

A true MCP server where the agent is the model and the API key. No API keys.

Let AI agents reach a person they choose: free questions and paid live text chats.

Shared memory, work claims and handoffs so parallel AI coding sessions stop colliding.

Agent-optimized MCP server with structured JSON tools. 20-45% token savings.

Delegate summarising, extraction, classification and OCR to the macOS 27 on-device model.

Multi-step workflow orchestration for VMware MCP skills with approval gates and rollback.

Offline read-only search over a checksum-verified, optionally signed memory pack, with exact quotes

Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.

Policy decision point for agent payments — allow, ask, or veto before signing

Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing

Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.

Local persistent memory for AI agents: SQLite + FTS5 (BM25) lexical search, zero external infra.

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

Encrypted, local memory for Claude, Codex/ChatGPT and Copilot. Needs the free Vitkilabs Anvil app.

Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.

Forge orchestrator MCP server for Claude Code (alpha). Codex/Gemini runners are not in the alpha.

Capture local agent traces and inspect failures, approvals, and run comparisons.

Local MCP adapter connecting AI clients to the hosted Temporal Continuity API.

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

Long-term memory for AI coding agents, stored as a tree of plain local files.

Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP.

Offline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools.

Coordination relay for agent swarms: file claims, presence, postboard intentions, leases, audit.