wadachi · persistent memory · MCP

Your sessions leave tracks.

Wadachi (轍): the tracks wheels leave in a road. Your AI forgets everything between sessions — re-reading files, re-deriving architecture, re-debating solved problems. Wadachi gives it tracks that stay.

PyPI · v0.13.0 CI · passing MIT · local-first · no telemetry
The problem → the solution

Stop re-explaining. Start compounding.

every other session

Starts from zero. Every time.

The model re-reads the same files, re-discovers the same patterns — and you type the same reminders, again:

with wadachi

One call. Everything back.

get_context loads project, memories, decisions and what needs review — ~400 tokens, then it compounds:

What's inside

Memory that doesn't just store — it thinks.

Most memory tools make knowledge searchable. Wadachi makes it active: it connects, revises, reflects, and learns how you work.

Persistent memory

Knowledge stored as plain markdown files with SQLite metadata. Survives across sessions, human-readable, editable by hand. Every edit is versioned — nothing is lost.

Semantic search

Finds memories by meaning, not keywords. Powered by local embeddings via fastembed — no API calls, no cloud, no cost. Runs entirely on your machine.

Auto-context

The killer tool. get_context detects your project, gathers the relevant memories and recent decisions, and hands your AI everything it needs in one call.

Decision log

Not just what you know — what you decided and why. Each decision keeps its rationale and the rejected alternatives, so no choice gets re-debated.

Constellation graph

An entity knowledge graph over your brain. recall_associative spreads activation along citation, semantic and shared-entity edges — surfacing connected memories even when the words don't match.

Belief revision

Memories are beliefs with an epistemic envelope. Wadachi flags what's gone stale or been superseded, so a session opens knowing what it can no longer trust.

Reflect & insights

Thinks across memories: surfaces cross-project analogies and non-obvious connections recall can't reach, proposed as insights you accept or reject.

Procedural memory

Notices recurring incidents and proposes always-on rules for review — your brain learning not just facts, but how to act. Read-only: it suggests, never edits.

How it works

Four steps. Then it compounds.

1

Connect the MCP server

One command wires Wadachi into Claude Code, Claude Desktop, Cursor — any MCP client.

2

Register your projects

Map filesystem paths to a project name. Wadachi auto-detects which one you're in and scopes memories accordingly.

3

Start with context

Every session opens with get_context — the relevant brain is loaded before the first file is touched.

4

Store as you go

Bugs, decisions, configs, patterns — saved the moment they're figured out. The brain grows; each session starts faster.

Why wadachi

Yours. Local. Honest.

The memory space is crowded and full of good tools. Here is where wadachi actually differs — and where the alternatives are genuinely strong.

wadachi 轍Mem0 / ZepSupermemory
Where your memories live Markdown files on your disk — an Obsidian vault, an OKF bundle Their cloud (self-host possible)Their cloud
Telemetry None. Ever.Product analyticsProduct analytics
Cost to run $0 — local embeddings, no API calls API-meteredSubscription
Memory model Beliefs that go stale, decisions with provenance (why), time-travel (as_of), sleep consolidation Facts + graph (Zep: temporal graph, excellent) Documents + recall
Scale & teams Single-brain, one human — by design Multi-tenant, production-scale Team sharing
Managed convenience You run it (one pipx install) Hosted, zero opsHosted, zero ops

Honest summary: if you need multi-tenant scale or a managed service, use the alternatives — they are good at it. If you want a brain that is yours, readable on disk, free to run, and that reasons about what it believes — that is what wadachi is for.

31MCP tools
$0API cost · runs local
md + SQLitehuman-readable store
MITopen source

Give your AI a memory.

Three commands, and you never re-explain your codebase again.

# install (semantic search included, runs locally)
pipx install "wadachi[semantic]"

# guided setup: brain dir, database, Claude Code registration
wadachi init

# restart Claude Code — your AI now remembers