Mem Forge

Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.

LLM Mart 0 views 122 listing impressions

Give every agent your team's brain on day one.

The memory layer for AI agents. Everything your team knows. Cited, and always up to date. Built from your docs, tickets and chat.

CI License Apache 2.0 Status beta

The open-source edition runs on your machine. The Team Cloud Edition is on the way: we host it and provide the models, your team just subscribes. Join the waitlist.

Why MemForge

  • Turns your team's wiki, tickets and chat into memory your coding agents can search. On its own, a coding agent sees only the local checkout. MemForge syncs sources such as Confluence, Jira and Teams ahead of time and builds one memory from them, so agents search that memory instead of querying each tool. New sources plug into the same connector interface, so the list can keep growing.
  • Continuously detects stale facts and conflicts as your docs change. Each sync, on demand or on a schedule, rechecks the facts taken from changed docs and keeps, replaces or retires each one. New facts are also compared with what's already in memory. When it finds two docs that disagree, the agent gets both, with a note saying they conflict or which is newer.
  • Gives agents precise facts, not documents that blow up their context. At sync, a model turns your sources into memories: precise facts and decisions that keep their conditions and exceptions. Agents search them over MCP by keyword, and by meaning if you add an embedding model. Search results carry no document text, so a full document enters the context only when the agent asks for it.
  • Always justifies each fact with its real source. Every fact from a source cites the passage behind it and, where one exists, links to the original page, ticket or file. If no source supports a fact any more, it is retired. The citation can be a paraphrase, so MemForge also keeps the source text it read, and you or the agent can open it to confirm.
  • Runs on your machine, with team sharing on the way. The open-source edition is Apache-2.0 and single-user, with local storage and your own model keys. Source text goes to the model providers you choose, and the agent plugins don't record your sessions. The hosted Team Cloud Edition will give the whole team one shared memory.

Quick start

Beta. APIs, storage formats and plugin packaging may change. An upgrade that migrates your data saves a recovery point first (Upgrading).

You need Docker with Compose v2 and an API key for OpenRouter, OpenAI or Anthropic.

From the project's README.

Related servers

Read and write RAGE Package Format archives

23 views

Let LLM help you achieve your regression analysis with Stata

21 views

Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.

21 views

vSphere with Tanzu (VKS): Namespace and TanzuKubernetesCluster lifecycle. Requires vSphere 8.x+.

20 views