All notable changes to this project will be documented in this file.
- Reworked the README first screen around the "3-file memory system" positioning.
- Added a copy-first
starter-kit/with minimalAGENTS.md, memory files, and per-agent prompts. - Added comparison, compatibility, flow diagram, demo walkthrough, launch copy, and v0.6.0 release checklist docs.
- Added the optional unified
deja-vu init,deja-vu doctor, anddeja-vu explainCLI. - Split read-only source tests from npm pack verification with
test:src:readonlyandtest:pack. - Updated scripted recall to distinguish missing setup as
not_initialized.
- Made remember/writeback a first-class companion to recall with a post-task writeback routing table in the README, protocol, workflow, and AGENTS template.
- Added
writeback_hintguidance to scripted memory scans so recall naturally leads into durable memory maintenance. - Added
deja-vu-feedback-reportto aggregate recall feedback into maintenance suggestions for aliases, weights, compaction, and route cleanup. - Expanded memory linting beyond JSONL into Markdown lifecycle checks for summaries, decisions, open loops, frontmatter, supersession, and transcript-like records.
- Added tests for writeback hints, feedback reporting, Markdown memory linting, and package binary inclusion.
- Reaffirmed Deja Vu as an ultra-light protocol-first memory system rather than a required package, service, daemon, vector database, or engine.
- Updated the README opening around the concrete adoption promise: stop re-explaining the repo to every new coding-agent chat.
- Added a 2-minute start path centered on
AGENTS.md,memory/summary.md, andmemory/impressions.jsonl. - Clarified that scripts, recall feedback, detailed records, and the TypeScript engine are optional scale-up layers.
- Added release notes for the 0.4.1 protocol-first activation patch.
- Reframed the README and package metadata around repo-local Markdown memory for AI coding agents.
- Added observable recall budget reporting to scripted scans and the TypeScript engine.
- Added recall feedback as a lightweight reward signal with
helpful,irrelevant,missed, andoverloadedoutcomes. - Added
memory/recall-feedback.jsonltemplates and example feedback records. - Expanded memory linting for feedback records, status values, weights, date formats, scope naming, and unsafe record paths.
- Updated protocol, workflow, scripted recall, storage, templates, and examples for Deja Vu Protocol v0.4.
- Updated package metadata for the 0.4.0 release.
- Added impression cue quality warnings to
deja-vu-lint-memoryfor sparse, oversized, duplicate, generic, and repeated keyword sets. - Updated the default summary generator to preserve decision, rationale, and trigger gist cues instead of only truncating source content.
- Updated the default chunker to preserve Markdown heading and paragraph boundaries before falling back to hard splitting.
- Added source tests for cue lint warnings, gist summaries, and boundary-aware chunking.
- Updated package metadata for the 0.3.1 patch release.
- Repositioned Deja Vu as a cue-first memory protocol centered on
task cue -> familiarity score -> minimal recall -> durable writeback. - Reduced the minimum adoption surface to
memory/summary.md,memory/impressions.jsonl, and project rules. - Reclassified
memory/decisions/,memory/open-loops/,memory/events/,memory/context/, andmemory/index.mdas recommended or optional artifacts. - Added a default recall budget: scan always, summary at most one file, details one to three records, and no full memory-tree loads unless explicitly requested.
- Updated protocol, workflow, storage, bootstrap, scripted recall, template, example, and AI-readable docs around low-token cue-first recall.
- Updated package metadata to version 0.3.0.
- Made engine impression scans token-only so query embeddings are deferred until chunk retrieval is needed.
- Added CLI
--memory-rootand--fileoptions and alignedmatchedwith weak/strong scan levels. - Added
deja-vu-scan-memoryanddeja-vu-lint-memorypackage binaries. - Added memory linting for impression schema, duplicate ids, and linked record paths.
- Updated adoption docs, handshake, templates, and example project to make impression-first recall the default path.
- Updated protocol naming to v0.2 and clarified project-local plain text storage.
- Added a protocol-level impression layer for compact keyword-first familiarity scans.
- Added scripted recall documentation and a default
scripts/dejavu-scan-memory.mjsscanner. - Added
memory/impressions.jsonlandmemory/events/templates for cheap long-term continuity. - Updated workflow, protocol, storage, bootstrap, and AGENTS templates around impression-first recall.
- Extended the optional TypeScript engine with
impressionTokensandscanImpressions(). - Added tests for scanning impressions without loading deeper memory.
- Repositioned Deja Vu as a protocol-first memory system for AI agents.
- Rewrote the root README around rules, workflow, and Markdown memory as the primary adoption path.
- Added the core protocol references:
docs/protocol.mddocs/workflow.mddocs/storage-markdown.md
- Added copyable project rules and memory templates under
docs/templates/. - Added
examples/protocol-project/as a repo-first example that works without npm or the optional engine. - Moved the semantic TypeScript engine into an explicitly optional documentation path under
docs/engine/. - Rewrote handshake, bootstrap, release, and AI-readable docs to match the new protocol-first framing.
- Updated package metadata to describe the npm package as an optional semantic recall layer.
- Fixed
npm run test:srcfor the current Node.js v24 environment by switching to a compatiblets-noderegistration path.
- Initial public release of Deja Vu.
- Added the familiarity-first semantic recall engine core.
- Added in-memory storage and vector adapters for zero-infrastructure local trials.
- Added runnable examples for basic recall, agent PM, chat memory, and task assistant flows.
- Added AI-readable integration docs, handshake guidance, and project rules templates.