Sam Valladares
5b90a73055
feat: Vestige v1.9.1 AUTONOMIC — self-regulating memory with graph visualization
...
Retention Target System: auto-GC low-retention memories during consolidation
(VESTIGE_RETENTION_TARGET env var, default 0.8). Auto-Promote: memories
accessed 3+ times in 24h get frequency-dependent potentiation. Waking SWR
Tagging: promoted memories get preferential 70/30 dream replay. Improved
Consolidation Scheduler: triggers on 6h staleness or 2h active use.
New tools: memory_health (retention dashboard with distribution buckets,
trend tracking, recommendations) and memory_graph (subgraph export with
Fruchterman-Reingold force-directed layout, up to 200 nodes).
Dream connections now persist to database via save_connection(), enabling
memory_graph traversal. Schema Migration V8 adds waking_tag, utility_score,
times_retrieved/useful columns and retention_snapshots table. 21 MCP tools.
v1.9.1 fixes: ConnectionRecord export, UTF-8 safe truncation, link_type
normalization, utility_score clamping, only-new-connections persistence,
70/30 split capacity fill, nonexistent center_id error handling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-21 02:02:06 -06:00
Sam Valladares
c29023dd80
feat: Vestige v1.7.0 — 18 tools, automation triggers, SQLite perf
...
Tool consolidation: 23 → 18 tools
- ingest merged into smart_ingest (single + batch mode)
- session_checkpoint merged into smart_ingest batch (items param)
- promote_memory/demote_memory merged into memory(action=promote/demote)
- health_check/stats merged into system_status
Automation triggers in system_status:
- lastDreamTimestamp, savesSinceLastDream, lastBackupTimestamp,
lastConsolidationTimestamp — enables Claude to conditionally
trigger dream/backup/gc/find_duplicates at session start
- Migration v6: dream_history table (dreams were in-memory only)
- DreamHistoryRecord struct + save/query methods
- Dream persistence in dream.rs (non-fatal on failure)
SQLite performance:
- PRAGMA mmap_size = 256MB (2-5x read speedup)
- PRAGMA journal_size_limit = 64MB (prevents WAL bloat)
- PRAGMA optimize = 0x10002 (fresh query planner stats on connect)
- FTS5 segment merge during consolidation (20-40% keyword boost)
- PRAGMA optimize during consolidation cycle
1,152 tests passing, 0 failures, release build clean.
2026-02-20 21:59:52 -06:00
Sam Valladares
ce520bb246
chore: license AGPL-3.0, zero clippy warnings, CHANGELOG through v1.6.0
...
License:
- Replace MIT/Apache-2.0 with AGPL-3.0-only across all crates and npm packages
- Replace LICENSE file with official GNU AGPL-3.0 text
- Remove LICENSE-MIT and LICENSE-APACHE
Code quality:
- Fix all 44 clippy warnings (zero remaining)
- Collapsible if statements, redundant closures, manual Option::map
- Remove duplicate #[allow(dead_code)] attributes in deprecated tool modules
- Add Default impl for CognitiveEngine
- Replace manual sort_by with sort_by_key
Documentation:
- Update CHANGELOG with v1.2.0, v1.3.0, v1.5.0, v1.6.0 entries
- Update README with v1.6.0 highlights and accurate stats (52K lines, 1100+ tests)
- Add fastembed-rs/ to .gitignore
- Add fastembed-rs to workspace exclude
1115 tests passing, zero warnings, RUSTFLAGS="-Dwarnings" clean.
2026-02-19 03:00:39 -06:00
Sam Valladares
495a88331f
feat: Vestige v1.6.0 — 6x storage reduction, neural reranking, instant startup
...
Four internal optimizations for dramatically better performance:
1. F16 vector quantization (ScalarKind::F16 in USearch) — 2x storage savings
2. Matryoshka 256-dim truncation (768→256) — 3x embedding storage savings
3. Convex Combination fusion (0.3 keyword / 0.7 semantic) replacing RRF
4. Cross-encoder reranker (Jina Reranker v1 Turbo via fastembed TextRerank)
Combined: 6x vector storage reduction, ~20% better retrieval quality.
Cross-encoder loads in background — server starts instantly.
Old 768-dim embeddings auto-migrated on load.
614 tests pass, zero warnings.
2026-02-19 01:09:39 -06:00
Sam Valladares
927f41c3e4
feat: Vestige v1.5.0 — Cognitive Engine, memory dreaming, graph exploration, predictive retrieval
...
28-module CognitiveEngine with full neuroscience pipeline on every tool call.
FSRS-6 now fully automatic: periodic consolidation (6h timer + inline every
100 tool calls), real retrievability formula, episodic-to-semantic auto-merge,
cross-memory reinforcement, Park et al. triple retrieval scoring, ACT-R
base-level activation, personalized w20 optimization.
New tools (19 → 23):
- dream: memory consolidation via replay, discovers hidden connections
- explore_connections: graph traversal (chain, associations, bridges)
- predict: proactive retrieval based on context and activity patterns
- restore: memory restore from JSON backups
All existing tools upgraded with cognitive pre/post processing pipelines.
33 files changed, ~4,100 lines added.
2026-02-18 23:34:15 -06:00
Sam Valladares
a92fb2b6ed
release: v1.1.3 — security hardening, edition 2024, dependency updates
...
Security:
- Fix RUSTSEC-2026-0007 (bytes integer overflow)
- Restrict SQLite database file permissions to 0600 on Unix
- Add 100KB size limit to intention descriptions (DoS prevention)
- Redact JSON-RPC payloads from debug logs (data leakage prevention)
- Update SECURITY.md with encryption docs and supported versions
Modernization:
- Upgrade Rust edition 2021 → 2024, MSRV 1.75 → 1.85
- Upgrade actions/checkout@v4 → v5, codecov/codecov-action@v3 → v5
- Update all dependencies to latest compatible versions
- Fix edition 2024 match ergonomics in compression.rs
Clippy fixes:
- Rename from_str → parse_name to avoid shadowing FromStr trait
- Replace .max().min() with .clamp()
- Replace sort_by with sort_by_key
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-12 03:19:07 -06:00
Sam Valladares
a680fa7d2f
fix: dedup on ingest, Intel Mac CI, npm versions, remove dead TS package
...
- Route ingest tool through smart_ingest (Prediction Error Gating) to
prevent duplicate memories when content is similar to existing entries
- Fix Intel Mac release build: use macos-13 runner for x86_64-apple-darwin
(macos-latest is now ARM64, causing silent cross-compile failures)
- Sync npm package version to 1.1.2 (was 1.0.0 in package.json, 1.1.0
in postinstall.js BINARY_VERSION)
- Add vestige-restore to npm makeExecutable list
- Remove abandoned packages/core/ TypeScript package (pre-Rust implementation
referencing FSRS-5, chromadb, ollama — 32K lines of dead code)
- Sync workspace Cargo.toml version to 1.1.2
Closes #5
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-12 02:57:03 -06:00
Sam Valladares
709c06c2fa
Change license to AGPL-3.0-only
2026-01-30 00:55:03 -06:00
Sam Valladares
f9c60eb5a7
Initial commit: Vestige v1.0.0 - Cognitive memory MCP server
...
FSRS-6 spaced repetition, spreading activation, synaptic tagging,
hippocampal indexing, and 130 years of memory research.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-25 01:31:03 -06:00
