Skip to content
Back to search

memforge

MarketplaceWorks with Claude CodeGitHub

MemForge plugin marketplace for agent memory integrations.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/dodo-labs-ai/mem-forge with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/dodo-labs-ai/mem-forge'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/dodo-labs-ai--mem-forge/badge.svg)](/listings/dodo-labs-ai--mem-forge)

HTML

<a href="/listings/dodo-labs-ai--mem-forge"><img src="/api/listings/dodo-labs-ai--mem-forge/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You need Docker with Compose v2 and an API key for a model provider (OpenRouter, OpenAI or Anthropic), or a model server such as Ollama.

git clone https://github.com/dodo-labs-ai/mem-forge.git && cd mem-forge
cp .env.example .env
docker compose up --build

Open the admin UI at http://localhost:5174 and choose a generation model and an embedding model in Settings. Then install the agent plugin:

# Claude Code (inside a session)
/plugin marketplace add dodo-labs-ai/mem-forge
/plugin install memory@memforge
# Codex
codex plugin marketplace add dodo-labs-ai/mem-forge
codex plugin add memory@memforge

Open **Sources** in the admin UI to connect Confluence, Jira or another source, then start a new agent session and ask:

Before you change this, check MemForge for decisions and conventions that
apply, and show the source for each one you rely on.

When you settle something in a session, ask the agent to remember it. It shows you the memory first and saves it after you confirm.

The [quickstart](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md) covers model settings, [plugin routing](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md#plugin-routing) for a hosted endpoint or more than one workspace, local folders, the host CLI and network details.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "memforge",
  4. "description": "MemForge plugin marketplace for agent memory integrations.",
  5. "owner": {
  6. "name": "MemForge Team"
  7. },
  8. "plugins": [
  9. {
  10. "name": "memory",
  11. "description": "MemForge MCP memory integration for Claude Code.",
  12. "source": "./integrations/claude-code/memforge-memory",
  13. "category": "productivity"
  14. }
  15. ]
  16. }
README.md · README · 230 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <h1><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/logo.svg" width="36" align="absmiddle" alt=""> MemForge</h1>
  2. **Give every agent your team's brain on day one.**
  3. The memory layer for AI agents. Everything your team knows. Cited, and always
  4. up to date. Built from your docs, tickets and chat.
  5. <p>
  6. <a href="https://github.com/dodo-labs-ai/mem-forge/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/dodo-labs-ai/mem-forge/actions/workflows/ci.yml/badge.svg"></a>
  7. <img alt="License Apache 2.0" src="https://img.shields.io/badge/license-Apache--2.0-blue">
  8. <img alt="Status beta" src="https://img.shields.io/badge/status-beta-3b82f6">
  9. </p>
  10. <p align="center">
  11. <picture>
  12. <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/demo-dark.gif">
  13. <img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/demo-light.gif" alt="On day one, a new hire asks a coding agent how to fix a ticket about a customer charged twice. Without team memory the agent starts patching the payment code. With MemForge it checks team memory first: not a bug, a pending card hold, citing the support playbook and the team's decision log in Notion. The admin UI shows the connected sources syncing on their own, and a memory the decision log updated." width="100%">
  14. </picture>
  15. </p>
  16. <p align="center">
  17. The open-source edition runs on your machine. The <b>Team Cloud Edition</b> is on the way:
  18. we host it and provide the models, your team just subscribes.
  19. <a href="https://github.com/dodo-labs-ai/mem-forge/discussions/13">Join the waitlist</a>.
  20. </p>
  21. ## Why MemForge
  22. - **Turns your team's wiki, tickets and chat into memory your coding agents can
  23. search.** On its own, a coding agent sees only the local checkout. MemForge syncs
  24. sources such as Confluence, Jira and Teams ahead of time and builds one memory
  25. from them, so agents search that memory instead of querying each tool. New sources
  26. plug into the same
  27. [connector interface](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/architecture.md#adding-a-source),
  28. so the list can keep growing.
  29. - **Continuously detects stale facts and conflicts as your docs change.** Each sync,
  30. on demand or on a schedule, rechecks the facts taken from changed docs and keeps, replaces
  31. or retires each one. New facts are also compared with what's already in memory.
  32. When it finds two docs that disagree, the agent gets both, with a note saying they
  33. conflict or which is newer.
  34. - **Gives agents precise facts, not documents that blow up their context.** At sync,
  35. a model turns your sources into memories: precise facts and decisions that keep
  36. their conditions and exceptions. Agents search them over MCP by keyword, and by
  37. meaning if you add an embedding model. Search results carry no document text, so a
  38. full document enters the context only when the agent asks for it.
  39. - **Always justifies each fact with its real source.** Every fact from a source cites
  40. the passage behind it and, where one exists, links to the original page, ticket or
  41. file. If no source supports a fact any more, it is retired. The citation can be a
  42. paraphrase, so MemForge also keeps the source text it read, and you or the agent
  43. can open it to confirm.
  44. - **Runs on your machine, with team sharing on the way.** The open-source edition
  45. is Apache-2.0 and single-user, with local storage and your own model keys. Source
  46. text goes to the model providers you choose, and the agent plugins don't record
  47. your sessions. The hosted
  48. [Team Cloud Edition](https://github.com/dodo-labs-ai/mem-forge/discussions/13)
  49. will give the whole team one shared memory.
  50. ## Quick start
  51. > **Beta.** APIs, storage formats and plugin packaging may change. An upgrade
  52. > that migrates your data saves a recovery point first
  53. > ([Upgrading](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md#upgrading)).
  54. You need Docker with Compose v2 and an API key for OpenRouter, OpenAI or
  55. Anthropic.
  56. **Let your agent set it up.** Paste this into Claude Code or Codex:
  57. ```text
  58. Set up MemForge for me. Fetch this guide with curl and follow it exactly:
  59. https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/docs/agent-setup.md
  60. ```
  61. The agent starts MemForge and installs its plugin, then hands you the admin UI
  62. to enter your model key and connect a source, so your keys never pass through
  63. the agent.
  64. <details>
  65. <summary><b>Or set it up yourself</b> with Docker Compose, in 5 steps</summary>
  66. 1. **Start MemForge.**
  67. ```bash
  68. git clone https://github.com/dodo-labs-ai/mem-forge.git && cd mem-forge
  69. git checkout -q "$(git describe --tags --abbrev=0 --match 'memforge-ai-v*')"
  70. cp .env.example .env
  71. docker compose up
  72. ```
  73. The second line moves to the latest release. Compose pulls that release's
  74. prebuilt images when it has them, and otherwise builds them from the
  75. checkout, which takes several minutes. The admin UI is at
  76. http://localhost:5174.
  77. 2. **Choose models.** In **Settings**, choose a generation model, which writes
  78. the memories, and optionally an embedding model for semantic search. After
  79. **Save and validate**, each one shows **Ready**.
  80. 3. **Connect a source.** In **Sources**, add a source, such as a Confluence
  81. space or a GitHub repository, and run a sync. Turn on
  82. **Sync automatically** to keep it current. The source shows the memories it
  83. made as the sync runs.
  84. 4. **Install the agent plugin.**
  85. ```text
  86. # Claude Code (inside a session)
  87. /plugin marketplace add dodo-labs-ai/mem-forge
  88. /plugin install memory@memforge
  89. ```
  90. ```bash
  91. # Codex
  92. codex plugin marketplace add dodo-labs-ai/mem-forge
  93. codex plugin add memory@memforge
  94. ```
  95. 5. **Ask.** Start a new agent session in your project and ask:
  96. ```text
  97. Before you change this, check MemForge for decisions and conventions that
  98. apply, and show the source for each one you rely on.
  99. ```
  100. The agent answers with the memories that apply and names the source of each.
  101. </details>
  102. The [quickstart](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md) covers every model provider,
  103. local folders, the host CLI and network details.
  104. ## How it works
  105. ```mermaid
  106. flowchart LR
  107. subgraph You["Your machine"]
  108. CC["Claude Code / Codex"]
  109. Plugin["MemForge plugin"]
  110. API["MemForge"]
  111. Extract["Write short memories,<br/>each citing its source"]
  112. Recheck["Recheck when a source changes,<br/>link related memories"]
  113. Store[("Local storage")]
  114. end
  115. Docs["Your team's wikis, tickets,<br/>repositories and chat"]
  116. CC --> Plugin
  117. Docs -- "sync" --> API
  118. API --> Extract --> Recheck --> Store
  119. Plugin -- "search, read a memory,<br/>open its source" --> API
  120. API -- "read" --> Store
  121. ```
  122. 1. **Sync.** Connectors read your docs, tickets and chat, on a schedule or
  123. when you ask.
  124. 2. **Extract.** A model turns each source into short memories, each citing the
  125. passage it came from.
  126. 3. **Recheck.** When a source changes, the memories built on it are kept,
  127. replaced or retired, and related memories are linked.
  128. 4. **Recall.** Agents search memory and open its sources over MCP.
  129. More detail: [architecture overview](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/architecture.md).
  130. ## Integrations
  131. MemForge sits between the systems where your team writes things down and the
  132. agents that do the work.
  133. **Agent integrations**
  134. <p>
  135. <img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/claude.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Claude&nbsp;Code&nbsp;&nbsp;&nbsp;
  136. <picture><source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/openai-dark.svg"><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/openai-light.svg" width="18" height="18" align="absmiddle" alt=""></picture>&nbsp;Codex
  137. </p>
  138. **Memory sources**
  139. <table>
  140. <tr>
  141. <td>Docs and wikis</td>
  142. <td nowrap>
  143. <img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/confluence.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Confluence&nbsp;&nbsp;&nbsp;
  144. <picture><source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/notion-dark.svg"><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/notion-light.svg" width="18" height="18" align="absmiddle" alt=""></picture>&nbsp;Notion&nbsp;&nbsp;&nbsp;
  145. <picture><source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/github-dark.svg"><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/github-light.svg" width="18" height="18" align="absmiddle" alt=""></picture>&nbsp;GitHub&nbsp;Pages&nbsp;&nbsp;&nbsp;
  146. <picture><source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/github-dark.svg"><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/github-light.svg" width="18" height="18" align="absmiddle" alt=""></picture>&nbsp;GitHub&nbsp;repo&nbsp;docs&nbsp;&nbsp;&nbsp;
  147. <img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/folder.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Local&nbsp;folders
  148. </td>
  149. </tr>
  150. <tr>
  151. <td>Tickets</td>
  152. <td nowrap><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/jira.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Jira</td>
  153. </tr>
  154. <tr>
  155. <td>Chat</td>
  156. <td nowrap><img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/teams.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Teams</td>
  157. </tr>
  158. <tr>
  159. <td>Planned</td>
  160. <td nowrap>
  161. <img src="https://raw.githubusercontent.com/dodo-labs-ai/mem-forge/main/.github/assets/icons/obsidian.svg" width="18" height="18" align="absmiddle" alt="">&nbsp;Obsidian
  162. </td>
  163. </tr>
  164. </table>
  165. [Add a source](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md#4-add-a-source) lists what each one syncs and
  166. how to scope it. Need one that is missing?
  167. [Vote for the next source](https://github.com/dodo-labs-ai/mem-forge/discussions/12).
  168. ## Limits
  169. - The open-source edition runs for one person on one machine. It has no
  170. accounts or authentication and listens on `127.0.0.1` only, so do not expose
  171. it on a network. For memory your whole team shares, join the
  172. [Team Cloud Edition waitlist](https://github.com/dodo-labs-ai/mem-forge/discussions/13).
  173. - Model extraction and semantic judgments can miss useful knowledge or make
  174. mistakes. Check the cited Evidence before relying on a consequential claim.
  175. - A generation model is required; without one, syncs store content but create
  176. no memories.
  177. ## Documentation
  178. - [Quickstart](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/quickstart.md): setup, models, plugins, sources, CLI,
  179. development from source
  180. - [Docs index](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/README.md): quickstart, architecture, API and release guides
  181. - [How MemForge compares](https://github.com/dodo-labs-ai/mem-forge/blob/main/docs/comparison.md): when to choose MemForge and when
  182. another tool fits better
  183. - [Contributing](https://github.com/dodo-labs-ai/mem-forge/blob/main/CONTRIBUTING.md)
  184. ## License
  185. Apache License 2.0. See [LICENSE](https://github.com/dodo-labs-ai/mem-forge/blob/main/LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.