vibe-cognition · Claude Code plugin

Your codebase, with a memory of why.

vibe-cognition is a fully local MCP server that captures your project's decisions, failures, discoveries, constraints and patterns as Claude works — then injects that context into every future session. It lives in your repo, travels with your team, and never touches a third-party server.

MIT licensed100% localNo API keys29 MCP toolsGit-committedMulti-agent safeCross-project
install · 3 steps
# needs uv (https://astral.sh/uv) — it handles Python for you
$ claude plugin marketplace add https://github.com/Haagndaazer/colton-claude-plugins
$ claude plugin install vibe-cognition@coltondyck

# restart Claude Code. first start installs deps (~60s)
# and downloads a ~250MB local embedding model, once.
# then: ask Claude to run get_status, or just start working.
The two things nobody else does

Memory across projects. Many agents, zero conflicts.

cognition_load_project

Load another project's memory

Working on the app but need to know why the API team dropped a field? Load that repo's cognition graph read-only and search it alongside your own. Decisions, failures and constraints from sibling projects become context, not folklore — and the embedding-model guard tells you exactly how much to trust the match.

append-only journal

Many agents, reading and writing at once

Run a manager and four subordinates against the same project and they all record and search simultaneously — no locks to fight over, no corrupted graph, no merge conflicts. The journal is append-only and every node is content-addressed, so concurrent writers simply interleave. Git merges it like any other log.

Your data stays your data

Local only. Source-controlled. Shared with your team, not with us.

  • Nothing leaves your machine. Embeddings, vector search, the graph and the dashboard all run locally. There is no Acrylic Code server in the loop, no account, no API key. The only optional network call is a once-a-day read-only version check to GitHub — and you can turn it off.
  • Built to be committed to git. The cognition journal is a plain file in your repo. Commit it, branch it, review it in pull requests like any other source. Knowledge moves with the code, not with a SaaS subscription.
  • Shared cognitive context for the whole team. When a teammate clones the repo, their Claude starts with the same history: what was decided, what failed, what's off-limits and why. New people — and new agents — stop re-learning the hard way.
  • People and provenance. Register who's on the team; every node carries who recorded it, whether a human or an agent, so you can weigh context by its source.
What it captures

Not what the code does. Why it's like that.

Git stores every change. Nobody stores the reasons. vibe-cognition records decisions (with the alternatives you rejected), failures, non-obvious discoveries, constraints, incidents, patterns, reusable workflows and tasks — and links them into a graph Claude can search in natural language: "why did we drop the Live API?"

decision
Pivoted from Live API TTS to REST teacher after verbatim reading failed on conversational text.ref: commit 4a2f1c · rejected: retry with stricter prompt
└─ led_to ↓
fail
Live transport dropped mid-sentence language markers under load; 3 of 10 test runs mispronounced.ref: issue #212
└─ resolved_by ↓
pattern
Inline <lang:xx> markers → a single Chirp3 HD TTS call; never split one reply across voices.curated · 4 supporting nodes
constraint
Teacher must explain in the learner's native language; target language only for examples and practice.severity: high · injected at session start
The dashboard

See the whole brain of the project — locally.

Type /vibe-dashboard in Claude Code and a read-mostly web console opens on 127.0.0.1, token-protected, nothing leaving your machine. It's organized like a project tool, not a hairball: seven views, one shared detail drawer.

vibe-cognition dashboard Overview: task stats, active constraints, recent episodes
Overview — open / in-progress / blocked tasks, what's done this week, documents and workflows, the project's active constraints with severity and who recorded them, recent episodes and incidents.
vibe-cognition dashboard Board: kanban of tasks with epics, priority and provenance
Board — a kanban of Open / In progress / Blocked / Done, grouped by epic, with priority, creator, claimant and claim age. Toggle to a tree view of the epic → subtask hierarchy.
vibe-cognition dashboard Graph: force-directed constellation of 1,373 nodes
Graph — the constellation itself: 1,373 nodes and 3,805 edges from one real project, colored by type. Pan, zoom, click a node to open it. Kept for curation debugging — spotting clusters with no edges.
  • Workflows — HEAD-only procedure cards with their version chain (v3 ⟵ v2 ⟵ v1) inline.
  • Documents — every stored spec/PDF with freshness (unchanged / modified / missing), cited-by count and a download link.
  • Activity — a chronological feed across decisions, fails, discoveries, incidents and patterns, filterable by type and author.
  • People — the registered roster with role and seniority; every node shows who recorded it, human or agent, verified or not.
  • Detail drawer — click anything: full node, provenance, related nodes by edge type, and a conflict banner if it's been contradicted or superseded.
  • Search — natural-language search across the whole history, powered by the local embedding index.
What's in the box

Everything bundled. Nothing to configure.

MCP server

29 tools

Record, search, trace chains of reasoning, manage tasks and workflows, store documents, register people — all from inside Claude Code.

hook

Context at session start

A SessionStart hook injects active constraints, recent patterns, decisions and incidents, so Claude opens every session already briefed.

/vibe-curate

A background curator

Subagents add semantic edges — led_to, supersedes, contradicts — hunt for conflicts, and summarize clusters. You never hand-author a graph.

search

Semantic, and local

Natural-language search over the whole history using an on-device embedding model (nomic-embed, or Ollama if you prefer). No cloud round-trip.

/vibe-dashboard

A local dashboard

Overview, kanban board, workflows, documents, activity feed, people, and the graph itself — on 127.0.0.1, token-protected, read-mostly.

/vibe-backfill

Backfill from git

Already have history? Generate episodes from commits you haven't captured yet, watermark-based, however far back.

How a session goes

Record. Curate. Recall.

Record

As Claude works it calls cognition_record for decisions, fails and discoveries, citing the commit or issue. Documents you hand it are stored and linked too.

Curate

Run /vibe-curate. A background orchestrator proposes and commits semantic edges and cluster summaries — so the graph stays a graph, not a pile of notes.

Recall

Next session, the hook briefs Claude automatically, and cognition_search answers "how did we get here?" before anyone re-litigates a settled decision.

Stop re-explaining your codebase to Claude.

Free, open source, local. Install from the Acrylic Code marketplace and your next session starts with context.

Install vibe-cognition

Pairs with teammate-comms for multi-agent teams · All plugins