memhub
v0.103.0by XTraceAI · author: XTrace
XTrace MemHub team memory: search_memory / save_artifact / import_conversation MCP tools plus skills for setup, login, onboarding, artifact upload, session import, team-memory recall, session handoff, spec-driven development, Rulebook rule authoring (create-rule) and a team's first Rulebook, tested starter rules fitted to the repo, and rules proposed from CLAUDE.md + past sessions (start-rulebook), and PR babysitting. A rule lives in a RULEBOOK: a container with its own membership, so it reaches exactly the people that book binds; the authoring skills resolve which book it lands in and offer to create one when there is none. Session auto-capture ships through the host-native plugin layer (hooks are outside the Agent Plugins spec). Session ↔ PR linking: after a call that addresses GitHub (`gh pr …`, a `curl`/`gh api` REST request, or a GitHub MCP tool) whose output names exactly one pull request, a PostToolUse hook asks the backend one question and injects one instruction, a session that ran `gh pr create`, or the GitHub MCP create tool, links itself unconditionally (opening it is work the session did, and a PR has many sessions), while every other GitHub call, a hand-rolled `curl` POST included, leaves the authorship judgment to the agent, and an org with no GitHub integration is told once that connecting it is what links sessions to shipped code. The hook is stateless apart from one short-lived negative answer (an enabled org with GitHub disconnected, cached 30 minutes per credential, and never inferred from a reply that merely says the feature is off) and degrades to silence on every failure. Two skills complete it: link-pr (link this or a named session by hand, also the answer for a PR opened by a script or CI helper, which is deliberately not detected) and find-contributing-sessions (map your own unlinked PRs, or the ones you name, to the sessions on this machine that wrote their code: scan local session history once, rank the candidates per PR by the evidence that matched, and link the ones you approve). The agent records ONE work type for a pull request it links (feat, fix, chore, docs, perf, refactor, other), and only when the PR has none yet, the first label is permanent, and asking again would cost the link, not just the type. Spec workflows: spec-work guides implementation, spec-check freshly reviews changes, and spec-maintain offers local/cloud bootstrap and reviewable Git or Brain proposals through the shared spec entry point. A companion animal draws what the plugin is doing in the band above the prompt, one per session picked from its session id (/goose, /hippo, /penguin and /shiba switch it for the session; `always` pins one for every session): asleep while the session is idle, awake and watching while Claude answers or the person types, and up announcing each Rulebook rule that fires, crossly when one blocked the call, or presenting a rule the harness just proposed with Activate / Reject / Later buttons (activating takes a rulebook admin; the animal says so to anyone else). Clicking the ♥ beside it pets it, and a proposal's rule↗ opens that rule in MemHub Studio. It needs Claude Code's function-hook runtime, which /memhub:companion turns on and persists.
What memhub does, in the publisher's words
MemHub gives coding agents shared team memory: interactive MCP tools for searching and saving knowledge, automatic session capture, situated directive recall, and workflows for artifacts, specs, handoffs, rules, and PR review. The same memhub plugin supports Claude Code, OpenAI Codex, and Cursor through each host's native plugin system.
This repository publishes the memhub plugin to all three hosts. It also contains the Claude Code-only fleet plugin for coordinating parallel agents.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 17
- MCP servers
- 1
- Stars
- 2
- License
- Apache-2.0
- Repo created
- 2026-06-09
- Last pushed
- 2026-10-01
- Publisher type
- Organization
- Version
- 0.103.0
Links
Skills · 17
- companion
- create-rule
- Use when the user wants to create a team engineering rule for the Rulebook (e.g. "/memhub:create-rule", "add a rule that we never force-push", "make a rule for this mistake", "make it actually stop me"). Pins a when-X-then-Y sentence, drafts a deterministic check, and files it for review through th…
- find-contributing-sessions
- handoff-session
- Use when the user wants to hand off the current session/work to a teammate via MemHub (e.g. "hand this off to Alice", "handoff this session to Bob", "share my context with Carol so she can pick this up", "pass this work to X"). Creates a shareable agent brain holding a handoff brief, and shares it…
- import-session
- Use when the user asks to import, upload, or save a Claude Code, Codex, or Cursor session/conversation/transcript into MemHub or team memory (e.g. "import this session into memhub", "save session <id> to memhub", "put that conversation in an agent brain"). Ships the transcript via a terminal upload…
- link-pr
- login
- Use when the user wants to authenticate or re-authenticate the MemHub plugin, or when memory capture is not working because of auth (e.g. "log in to memhub", "memhub login", "authenticate memhub", "memhub says I'm not authenticated", "my sessions aren't being saved", "capture stopped working", "re-…
- onboard
- Use when a new user wants to set up MemHub / an agent brain for their repo, or asks to "onboard", "get started", "set up my brain", or "seed a brain from my work". Crosses the empty-brain cold start: creates the repo's agent brain, seeds it from a real Claude Code session, shows the compiled overv…
- pr-babysit
- Use when a PR should be babysat to green, poll its review bots (Cursor bugbot, OpenAI Codex) and CI, fix the real findings, push, and when clean save a PR review record to the repo's MemHub room (e.g. "babysit this PR", "watch PR 14 and fix the bot findings", or auto-armed by the memhub hook right…
- save-artifact
- Use when the user asks to save, store, or upload a file/document/spec to MemHub or team memory as an artifact (e.g. "save this spec to memhub", "store this doc as an artifact", "version this design doc in memhub"). Uploads the file's bytes via a terminal script, never call save_artifact directly o…
- search-memory
- Use when the user asks what the team knows, decided, discussed, or saved about a topic, or wants to check MemHub/team memory (e.g. "what do we know about X", "did we decide on Y", "search memhub for Z", "is there a spec for W"). Read-only: searches facts, episodes, artifacts, and documents.
- setup
- Use when the user asks to set up, repair, or verify the installed MemHub host integration, especially Codex automatic capture, PreToolUse directive recall, hook installation, or capture health. Installs the Codex user-hooks compatibility bridge idempotently while preserving unrelated hooks, then ch…
- spec-check
- spec-maintain
- spec-work
- spec
- Use when the user wants spec-driven development backed by team memory, create, revise, drift-check, or report on a spec held in MemHub (e.g. "start a spec for X", "save this as the team spec", "revise the spec", "did the spec change under me?", "what's the status of the retry-policy spec?"). Specs…
- start-rulebook
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- memhubstreamable-http
- https://api.memhub.xtrace.ai/mcp-server/mcp
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
memory · memhub · xtrace · team-memory · session-capture
Related by publisher and keywords
Cross-session memory and token savings for coding agents.
Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.
Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.
Search your synced Screenpipe history across devices. Requires Data Sync.
Project-scoped durable memory, recall, Skills, and governed context for AI agents.
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.
[](https://agentpluginsdirectory.com/plugins/memhub)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.