{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4mzwgg3dfudk","handle":"ensemble-mcp","url":"https://wellknown.network/agents/ensemble-mcp","links":{"self":"https://wellknown.network/agents/ensemble-mcp/record.json","html":"https://wellknown.network/agents/ensemble-mcp","markdown":"https://wellknown.network/agents/ensemble-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ensemble-mcp","status":"https://wellknown.network/api/v1/agents/ensemble-mcp/status","claim":"https://wellknown.network/agents/ensemble-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ensemble-mcp/claim.json","badge":"https://wellknown.network/agents/ensemble-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ensemble-mcp/history","tools":"https://wellknown.network/api/v1/agents/ensemble-mcp/tools"},"ard":{"identifier":"urn:air::server:ensemble-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ensemble-mcp","summary":"MCP server providing vector memory, drift detection, model routing, skills discovery, session management, and codebase indexing for AI-assisted development pipelines.","description":"# ensemble-mcp\n\nA **harness infrastructure layer** delivered as a Python MCP server — providing **vector memory**, **drift detection**, **model routing**, **skills discovery**, **session management**, **codebase indexing**, and **context compression** for AI agent pipelines.\n\nAll intelligence is local — zero LLM/API calls. Uses ONNX Runtime embeddings (~5ms), numpy cosine similarity, and SQLite storage.\n\n---\n\n## What is an Agent Harness?\n\n**Agent = Model + Harness.** A harness is every piece of code, configuration, and execution logic that wraps a model to turn it into a useful agent. Without a harness, a model can only take in text and output text — it can't maintain state, execute code, access tools, or learn from past work.\n\nA complete agent harness typically includes:\n\n- **System prompts & configuration** — instructions that shape agent behavior\n- **Tools, Skills & MCPs** — capabilities the agent can invoke\n- **Execution environment** — filesystem, bash, sandbox, browser\n- **Orchestration logic** — subagent spawning, handoffs, model routing\n- **Memory & context management** — compaction, skills, session persistence\n- **Hooks & middleware** — deterministic checks like linting, formatting, drift detection\n\n> *For a deeper dive, see [The Anatomy of an Agent Harness](https://www.langchain.com/blog/the-anatomy-of-an-agent-harness) by LangChain.*\n\n## Where ensemble-mcp Fits\n\nAgent harnesses like Claude Code, Codex, and Cursor provide the **execution layer** — filesystem, bash, sandbox. ensemble-mcp provides the **intelligence infrastructure layer** that plugs into any harness via MCP:\n\n```\n┌─────────────────────────────────────────────────────────┐\n│                    AGENT HARNESS                        │\n│                                                         │\n│  ┌───────────────────────────────────────────────────┐  │\n│  │            Execution Layer                        │  │\n│  │    (provided by Claude Code / Codex / Cursor)     │  │\n│  │                    …","publisher":null,"homepage":"https://github.com/LynkByte/ensemble/tree/main/docs","repository":"https://github.com/LynkByte/ensemble/blob/main/CHANGELOG.md","version":"0.1.0b7","license":"MIT License\n        \n        Copyright (c) 2026 Sanjaya De Silv…","protocols":["mcp"],"tags":["agent","ai","codebase-indexing","drift-detection","embeddings","mcp","model-routing","onnx","orchestration","vector-memory"],"pricing":null,"endpoints":[{"url":"pypi:ensemble-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"derived"},{"slug":"automation.orchestration","name":"Agent Orchestration","confidence":1,"provenance":"declared"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.882,"provenance":"derived"}],"categories":["automation","data","dev","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ensemble-mcp","registry":"pypi","observedAt":"2026-10-28T00:27:36.497Z","publishedAt":"2026-04-17T14:08:33.623773Z","latestVersion":"0.1.0b7"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ensemble-mcp","url":"https://pypi.org/project/ensemble-mcp/","firstSeenAt":"2026-09-09T15:21:34.854Z","fetchedAt":"2026-10-28T00:25:57.424Z","normalizedAt":"2026-10-28T00:25:57.424Z"}]},"firstSeenAt":"2026-09-09T15:21:34.854Z","updatedAt":"2026-10-28T00:27:36.497Z"}