Vestige

Local cognitive memory for MCP-compatible AI agents.

Your agent forgets project decisions between sessions. Vestige gives it local, inspectable memory.

Built on proven memory and retrieval ideas — FSRS-6 spaced repetition, prediction error gating, synaptic tagging, spreading activation, and memory consolidation — all running in a single Rust binary with a local dashboard. 100% local. Zero cloud.

Quick Start | Dashboard | How It Works | Tools | Docs

What's New in v2.1.22 "Sanhedrin Receipts"

v2.1.22 makes the optional Sanhedrin hook accountable enough to trust in daily agent work. Vetoes now leave local receipts, verification claims need real command evidence, and users can appeal stale or over-strict blocks from the dashboard.

• Receipt Lock. Claims like "tests passed", "build is green", or "lint is clean" are blocked unless the current transcript contains a matching successful command receipt.
• Screenshotable veto receipts. Sanhedrin writes ~/.vestige/sanhedrin/latest.json and latest.html with Claim -> Verdict -> Precedent -> Fix -> Appeal.
• Dashboard Verdict Bar. The dashboard shows PASS, NOTE, CAUTION, VETO, or APPEALED globally, expands into the receipt, and records stale/wrong/too-strict appeals.
• Claim ledger. Claim-mode Sanhedrin output now maps every extracted claim into structured JSON instead of treating the whole draft as one blob.
• Appeal training. Appeals are saved to appeals.jsonl and suppress future vetoes for the same claim fingerprint.

What's New in v2.1.21 "Agent-Neutral Hardening"

v2.1.21 tightens Vestige for normal use across MCP-compatible agents, without making Claude Code companion tooling part of the default path.

• Agent-neutral default. Stdio MCP remains the default transport; optional HTTP MCP is explicit with --http, --http-port, or VESTIGE_HTTP_ENABLED=1.
• Safer destructive actions. memory(action="delete") now requires confirm=true, matching purge, and the legacy delete_knowledge shim forwards that confirmation instead of bypassing it.
• Portable sync repair. Merge imports preserve purge tombstones, avoid INSERT OR REPLACE cascades, rebuild the vector index from a clean state, and write portable archive temp files with private Unix permissions.
• Release/package cleanup. Release builds check the embedded dashboard before packaging, publish checksums, and the npm installer rejects targets that do not have release assets.
• Any-agent memory protocol. The setup docs now include a short agent-agnostic memory protocol for Claude Code, Codex, Cursor, VS Code, Xcode, JetBrains, Windsurf, and other MCP clients.

What's New in v2.1.2 "Honest Memory"

v2.1.2 makes Vestige easier to trust in everyday work: literal lookups stay literal, purge really removes content, contradictions are inspectable, and updates no longer require a curl reinstall flow.

• Concrete search mode. Quoted strings, env vars, UUIDs, paths, and code identifiers now take a keyword/literal path that skips HyDE, semantic fusion, FSRS reweighting, competition, and spreading activation. Exact things like OPENAI_API_KEY, mlx_lm.server, and migration IDs land first.
• Irreversible purge. memory(action="purge", confirm=true) permanently removes memory content and embeddings, scrubs insight JSON references, detaches temporal-summary children, prunes graph edges, and keeps only a non-content deletion tombstone for sync/audit.
• First-class contradiction inspection. New contradictions MCP tool surfaces trust-weighted disagreements directly instead of hiding them inside deep_reference.
• Simple update flow. vestige update refreshes binaries. Claude Code Cognitive Sandwich companion files are opt-in with vestige update --sandwich-companion or vestige sandwich install.
• Pro waitlist preview. /dashboard/waitlist adds a local-first Solo Pro and Team Pro early-access surface. VITE_WAITLIST_ENDPOINT and VITE_SUPPORT_BOT_ENDPOINT are opt-in dashboard env vars, so no signup data is captured unless endpoints are configured.

What's New in v2.1.1 "Portable Sync"

v2.1.1 focuses on the biggest post-launch ask: move memories between machines without losing cognitive state. It also adds opt-in Qwen3 embeddings for higher-recall local retrieval.

• Exact portable archives. vestige portable-export / vestige portable-import preserve IDs, FSRS state, graph edges, suppression state, audit rows, and embedding blobs for Vestige-to-Vestige device transfer.
• Sync-safe merge storage. vestige portable-import --merge and vestige sync <archive> merge non-empty databases, apply delete tombstones, keep newer local memories, rebuild FTS, and push through a pluggable portable-sync backend. v2.1.1 ships the file backend for Dropbox, iCloud, Syncthing, Git, and shared folders.
• Qwen3 embeddings. Build with qwen3-embeddings, set VESTIGE_EMBEDDING_MODEL=qwen3-0.6b, and run vestige consolidate to re-embed existing memories. vestige health reports mixed-model stores before search quality is affected.
• Model-aware retrieval. Vestige now avoids comparing Qwen and Nomic vectors in the same search/dedup path.

What's New in v2.1.0 "Cognitive Sandwich Goes Local"

v2.1.0 adds an opt-in Claude Code hook harness around the existing Vestige MCP server. The MCP tool surface and database schema stay backward compatible, while preflight hooks can inject trusted memory context before Claude answers. The heavyweight Sanhedrin verifier is optional and can be enabled separately.

• Optional Sanhedrin Executioner. The post-response verifier is off by default. Users can enable it with an OpenAI-compatible endpoint on x86/Linux/Intel Mac, or add --with-launchd on Apple Silicon to run the local MLX Qwen backend.
• One-command Cognitive Sandwich installer. vestige sandwich install stages hook files and agents by default, removes old Vestige hook wiring, and leaves all Claude Code hook layers plus the 19 GB model path opt-in.
• Pulse hook backed by /api/changelog. Fresh dream and connection events can be injected into the next Claude Code prompt context without blocking the prompt.
• VESTIGE_DATA_DIR support. --data-dir now has an env-var fallback, tilde expansion, secure directory creation, and clear precedence docs.
• NPM release wrapper fixed. vestige-mcp-server@2.1.0 now downloads binaries from the matching v2.1.0 GitHub release tag instead of an old hardcoded release.

What's New in v2.0.9 "Autopilot"

Autopilot flips Vestige from passive memory library to self-managing cognitive surface. Same 24 MCP tools, zero schema changes — but the moment you upgrade, 14 previously dormant cognitive primitives start firing on live events without any tool call from your client.

• One supervised backend task subscribes to the 20-event WebSocket bus and routes six event classes into the cognitive engine: MemoryCreated triggers synaptic-tagging PRP + predictive-access records, SearchPerformed warms the speculative-retrieval model, MemoryPromoted fires activation spread, MemorySuppressed emits the Rac1 cascade wave, high-importance ImportanceScored (>0.85) auto-promotes, and Heartbeat rate-limit-fires find_duplicates on large DBs. The engine mutex is never held across .await, so MCP dispatch is never starved.
• Panic-resilient supervisors. Both background tasks run inside an outer supervisor loop — if one handler panics on a bad memory, the supervisor respawns it in 5 s instead of losing every future event.
• Fully backward compatible. No new MCP tools. No schema migration. Existing v2.0.8 databases open without a single step. Opt out with VESTIGE_AUTOPILOT_ENABLED=0 if you want the passive-library contract back.
• 3,091 LOC of orphan v1.0 tool code removed — nine superseded modules (checkpoint, codebase, consolidate, ingest, intentions, knowledge, recall, plus helpers) verified zero non-test callers before deletion. Tool surface unchanged.

What's New in v2.0.8 "Pulse"

v2.0.8 wires the dashboard through to the cognitive engine. Eight new surfaces expose the reasoning stack visually — every one was MCP-only before.

• Reasoning Theater (/reasoning) — Cmd+K Ask palette over the 8-stage deep_reference pipeline (hybrid retrieval → cross-encoder rerank → spreading activation → FSRS-6 trust → temporal supersession → contradiction analysis → relation assessment → template reasoning chain). Evidence cards, confidence meter, contradiction geodesic arcs, superseded-memory lineage, evolution timeline. Zero LLM calls, 100% local.
• Pulse InsightToast — real-time toasts for DreamCompleted, ConsolidationCompleted, ConnectionDiscovered, promote/demote/suppress/unsuppress, Rac1CascadeSwept. Rate-limited, auto-dismiss, click-to-dismiss.
• Memory Birth Ritual (Terrarium) — new memories materialize in the 3D graph on every MemoryCreated: elastic scale-in, quadratic Bezier flight path, glow sprite fade-in, Newton's Cradle docking recoil. 60-frame sequence, zero-alloc math.
• 7 more dashboard surfaces — /duplicates, /dreams, /schedule, /importance, /activation, /contradictions, /patterns. Left nav expanded 8 → 16