Show HN: Loom – Memory that follows the code you edit ClickHouse released Loom, an open-source, self-hosted MCP server that gives coding agents such as Claude Code, Codex and Cursor long-term shared memory, a repository code index and document search with citations. Loom stores agent context and index data in ClickHouse, can use Postgres at first boot for live memory and knowledge state, and supports namespaces, roles and scoped tokens in multi-user deployments. The project reports lower model cost for coding agents as a measured result. Shared memory, document search and code intelligence for AI agents. For Claude Code, Codex, Cursor and your own agents. English · 简体中文 https://github.com/ClickHouse/loom/blob/main/i18n/zh-CN/README.md · 日本語 https://github.com/ClickHouse/loom/blob/main/i18n/ja/README.md · 한국어 https://github.com/ClickHouse/loom/blob/main/i18n/ko/README.md · Português Brasil https://github.com/ClickHouse/loom/blob/main/i18n/pt-BR/README.md · Español https://github.com/ClickHouse/loom/blob/main/i18n/es/README.md What Loom is for what-loom-is-for · Benchmarks measured-results · Get started get-started · Capabilities why-loom · Integrations integrations · Documentation https://clickhouse.github.io/loom/ Loom is an open-source, self-hosted MCP server that gives your agents long-term, shared memory: what one agent learns in a session, the next agent or tool can find. In an authenticated team deployment, each agent uses a token scoped to namespaces and read or write roles. Check shared memory and denied access https://github.com/ClickHouse/loom/blob/main/docs/getting-started/connect-a-coding-agent.md share-a-team-namespace-with-separate-credentials . Agents connect through MCP, HTTP, Python or TypeScript. Self-host with Docker or on Kubernetes with the Helm chart https://github.com/ClickHouse/loom/blob/main/docs/operations/kubernetes.md ; agent context and index data live in ClickHouse https://github.com/ClickHouse/loom/blob/main/docs/use-cases/self-hosted-clickhouse.md , and a deployment can choose Postgres at first boot https://github.com/ClickHouse/loom/blob/main/docs/operations/postgres.md for live memory and knowledge state. The dashboard brings memories, repositories, tasks and runs into one place. - Long-term memory shared across your coding agents , with plugins that load context at session start and capture the session as it runs. Agent memory https://github.com/ClickHouse/loom/blob/main/docs/use-cases/agent-memory.md · Connect a coding agent https://github.com/ClickHouse/loom/blob/main/docs/getting-started/connect-a-coding-agent.md - Memory for an agent application , per user, from the Python or TypeScript SDK. Your first agent https://github.com/ClickHouse/loom/blob/main/docs/getting-started/first-agent.md - A multi-user MCP memory server with namespaces, roles and tokens. Multi-user mode https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md start-in-multi-user-mode · Namespaces and sharing https://github.com/ClickHouse/loom/blob/main/docs/features/namespaces-and-sharing.md - A code index of your repositories that coding agents query for definitions, callers and change impact. Code index https://github.com/ClickHouse/loom/blob/main/docs/use-cases/code-intelligence.md · Language support and limits https://github.com/ClickHouse/loom/blob/main/docs/features/code-index/overview.md language-support - Memories linked to the code they are about , which follow it through refactors, are flagged when it changes and appear when an agent reads or edits it. Memory linked to code https://github.com/ClickHouse/loom/blob/main/docs/use-cases/memory-linked-to-code.md - Lower model cost for coding agents , as measured measured-results below. Coding-agent cost https://github.com/ClickHouse/loom/blob/main/docs/use-cases/coding-agent-cost.md - Document search with citations RAG , including PDF, .docx and .pptx files the extractor service converts. Document search https://github.com/ClickHouse/loom/blob/main/docs/use-cases/document-search.md - Shared context for multi-agent workflows : shared memory, task inboxes and decisions. Multi-agent https://github.com/ClickHouse/loom/blob/main/docs/use-cases/multi-agent.md - Memory, recall, audit and erasure for autonomous agents. Autonomous agents https://github.com/ClickHouse/loom/blob/main/docs/use-cases/autonomous-agents.md - A record of agent work , with searchable conversations when recording is on , session briefs to resume from, runs with their goals, outcomes and model costs when supplied, and PR and tracker history. Runs and PR history https://github.com/ClickHouse/loom/blob/main/docs/use-cases/runs-and-pr-history.md Memory for a software factory. Loom gives implementation and review agents shared lessons, issue context and source provenance across sessions. Scope each principal's access with tokens, await required writes and task handoffs in your application, and recheck code-linked lessons against the current source before review. The same service supports multi-agent workflows and autonomous bots; your orchestration runs the agents, tests and approvals. Offering a tool does not guarantee the model uses it. Multi-agent workflow https://github.com/ClickHouse/loom/blob/main/docs/use-cases/multi-agent.md · Autonomous-agent memory https://github.com/ClickHouse/loom/blob/main/docs/use-cases/autonomous-agents.md Every use case, and when another tool fits better: use cases https://github.com/ClickHouse/loom/blob/main/docs/use-cases/index.md . Read Choosing memory for a software factory https://github.com/ClickHouse/loom/discussions/939 for memory architecture choices, data ownership and operating responsibilities. Loom is not an in-process library for one agent's short-lived memory, nor an agent framework. When Loom does not fit https://github.com/ClickHouse/loom/blob/main/docs/getting-started/overview.md when-it-does-not-fit | Evaluation | With Loom | Without Loom | Efficiency gain | Scope | |---|---|---|---|---| | Coding-agent answer quality | 0.84 | 0.78 | 20% lower model cost | 24 questions × 3 paired runs | | Coding-agent file localization | 96.4% | 91.4% | 21% lower model cost | 36 questions × 10 paired runs | | Memory vs full-history answers | 94% | 90% | 91% fewer reader prompt tokens | 100 paired LongMemEval-S questions | Both coding setups use Claude Code claude-sonnet-5 on the ClickHouse codebase; cost is the whole session's model bill, excluding Loom's server-side model calls, hosting and indexing. Answer quality measures coverage of a verified answer's key points, with a contradiction penalty. File localization counts whether the right file is among the up to three files the agent is asked to name at the end of its answer. The memory row compares retrieved memories with full conversation history using the same gpt-5 reader. Token savings exclude memory construction; the 94% vs 90% accuracy difference is descriptive, not statistically established. Separately, Loom's memory.ask configuration scored 96.6% answer accuracy on all 500 LongMemEval-S questions. This is a product evaluation with its own configured answer models, not the fixed-reader comparison above. Results are specific to the tested workloads. Protocols and reproducible artifacts https://github.com/ClickHouse/loom/blob/main/docs/benchmarks/results.md · detailed results benchmark-details · evaluate on your workload https://github.com/ClickHouse/loom/blob/main/docs/getting-started/evaluate.md - Personal use—the default: no login, localhost-only access and a dev/local namespace. One person can connect multiple agents. - Team use: authenticated accounts and namespace access controls. Start in multi-user mode from the first boot https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md start-in-multi-user-mode . Both modes support the same Loom features, including configured LLMs and embeddings. Single-user is not a reduced-feature edition. You can also switch an existing installation without deleting its data https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md 2-open-the-dashboard ; grant new accounts access to the existing namespaces. To try it with nothing installed, open it in a codespace: https://codespaces.new/ClickHouse/loom?quickstart=1 what it runs and who can reach it https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md try-it-in-github-codespaces For the default personal installation, with Docker installed on Windows, in a WSL 2 terminal where docker works: Docker Desktop with its WSL integration on, or Docker Engine installed in the distribution : curl -fsSL https://github.com/ClickHouse/loom/releases/latest/download/install.sh -o loom-install.sh && sh loom-install.sh && rm loom-install.sh Run it from your home directory, or another directory only you can write to https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md fast-path-released-image-no-clone . The installer starts Loom and ClickHouse, applies migrations and prints the dashboard URL: http://localhost:7777/ http://localhost:7777/ ; on a new install it then checks that a memory saves and reads back. On a terminal it also offers to connect the coding agents it finds Claude Code, Codex, VS Code and, on a new install, opens the dashboard. The image includes the server, workers, dashboard and Python, TypeScript and Go compiler indexers, plus the C++ one on amd64 ; TypeScript dependencies are prepared automatically. Quickstart and pinned releases https://github.com/ClickHouse/loom/blob/main/docs/getting-started/quickstart.md The installation lives in ~/.loom LOOM INSTALL DIR chooses another directory : the Compose file and the startup settings in ~/.loom/.env . Running the install command again upgrades in place and keeps your .env settings. Keep single-user mode localhost-only. For shared access, follow the team deployment guide https://github.com/ClickHouse/loom/blob/main/docs/operations/deployment.md identity-modes , including TLS. The stock installation boots without keys or network. Storage, the dashboard, structural code indexing and semantic search work, on a small local embedding model the image carries; the fake LLM gives no AI-generated answers. | Component | Configure for real use | Without configuration | |---|---|---| | Embeddings | Provider, embedding model, dimensions and API key. | local bge-small on CPU : semantic retrieval, weaker than a hosted model. | | LLM | Provider, model and API key. | fake-echo-1 : no meaningful extraction, summaries or answers. | Open Settings → Models & keys , choose both providers and models, enter their keys, then click Test & apply . No Docker restart is needed; changing the embedding space rebuilds the existing index. The dashboard's embedding choices are hosted providers: to keep local and add an LLM, set the LLM lines in ~/.loom/.env instead Models and keys https://github.com/ClickHouse/loom/blob/main/docs/getting-started/models-and-keys.md claude-for-the-llm . One OpenAI API key can serve both roles. Claude needs a separate embedding provider. OpenAI, Gemini and OpenAI-compatible embedding endpoints are supported. Your agent's CLI login or subscription does not supply Loom's provider keys. Prefer environment configuration? Edit ~/.loom/.env , then recreate the server: docker compose --project-directory "$HOME/.loom" up -d --force-recreate loom A key alone does not change the pinned models the local embedder and the fake LLM ; set the provider and model too. Saved dashboard settings take precedence over .env . Follow models and API keys https://github.com/ClickHouse/loom/blob/main/docs/getting-started/models-and-keys.md for provider recipes and health checks. Everything else is in one file. loom.example.yaml https://github.com/ClickHouse/loom/blob/main/loom.example.yaml lists every setting with its default and what it does, by area: the ClickHouse connection, timeouts and budgets, rate limits, workers, and the enabled switches that turn features on and off. Set any of them as LOOM