v0.1.3

What's Changed

• fix: anamnesis init now honors ANAMNESIS_HOME and ANAMNESIS_MACHINE_ID like every
  other component. It previously wrote config.json and ran its first sync against the default
  ~/.anamnesis even when the env said otherwise. Vanilla installs were unaffected; custom
  store homes and fleet scripts were. Re-running init on an existing store now also keeps the
  store's configured machine id instead of silently resetting it to the hostname.
• anamnesis.__version__ now reports the installed version (was stale at 0.0.1).

Full Changelog: v0.1.2...v0.1.3

v0.1.2

What's Changed

• chore(server): MCP registry ownership marker (0.1.2) by @oscardvs in #7

Full Changelog: v0.1.1...v0.1.2

v0.1.1

What's Changed

• Standalone dashboard: npx anamnesis-dashboard + anamnesis dashboard by @oscardvs in #3
• Launch-grade README by @oscardvs in #2
• feat(site): publish the real two-machine demo recording by @oscardvs in #4
• feat(dashboard): applications-menu launcher for the npm dashboard by @oscardvs in #5
• chore(server): MCP registry entry and uvx-friendly CLI alias (0.1.1) by @oscardvs in #6

Full Changelog: v0.1.0...v0.1.1

v0.1.0

Website: https://oscardvs.github.io/anamnesis/ · Docs: https://oscardvs.github.io/anamnesis/docs

uv tool install anamnesis-memory && anamnesis init

First launch release of the local-first core.

Highlights since 0.0.2

Memory quality loop

• LLM reflection distills session logs into durable notes (any OpenAI-compatible provider, config-driven, swappable)
• Recall-gated merge consolidates duplicates; nothing applies unless recall on your eval set holds
• Provenance-aware recall: every generated note carries source + confidence; superseded notes drop out of injection
• Durable writes: every path commits before it reindexes, so concurrent syncs cannot wipe work
• Opt-in auto-reflect at SessionEnd once a project crosses the unreflected threshold

Foundation

• Multi-tenant-shaped schema: user_id / workspace_id end to end (store, MCP tools, CLI)
• Eval harness: recall@k + inject-size measurement, sandboxed before/after experiments (anamnesis eval)
• Native importer mirrors Claude Code's own per-project memory into the store (anamnesis import)
• anamnesis config CLI + persistent per-store config.json; dashboard settings page

Install hardening (from a clean-room stranger audit)

• fastmcp is now a base dependency: the 0.0.2 one-line install registered an MCP server that could not start (0.0.1 and 0.0.2 are yanked)
• A local-only store can attach a remote later and just sync
• First sync of a fresh store is graceful and reports the history it pulled
• Sync failures print one line instead of a traceback

Honest numbers

• The token benchmark (bench/cross-machine-tokens/) is reproducible on a Pro/Max subscription, no API key needed. Measured: ~8% fewer input tokens on the same fresh-machine task, conventions known from the first turn. The earlier null result is published alongside.

v0.0.2

First public release of Anamnesis, a cross-machine, file-first memory layer for Claude Code.

What's in it

• Local-first store: markdown is the source of truth, indexed by SQLite FTS5 (WAL mode).
• MCP server (FastMCP): memory_search / memory_list / memory_status / memory_write / memory_sync.
• Cross-machine sync: git over your private Tailscale mesh; the index is rebuilt locally and never synced.
• Session hooks: SessionStart inject + background sync, SessionEnd and PreCompact capture.
• One-command setup: anamnesis init wires up the MCP server, hooks, the store, and a first sync.
• Git-like dashboard (Next.js): browse, full-text search, edit with write-back, and per-machine history.

Install

uv tool install anamnesis-memory && anamnesis init

The PyPI distribution is anamnesis-memory; the import package and CLI command are both anamnesis.

Pre-alpha: APIs and setup may still change.