Local cognitive memory for MCP-compatible agents, shipped as a single ~20MB Rust binary with a 25-tool MCP server, an Axum HTTP/WebSocket server, and a SvelteKit 3D memory dashboard. Implements neuroscience-grounded mechanisms — FSRS-6 spaced repetition, prediction-error gating, synaptic tagging, spreading activation, dual-strength model, and 'memory dreaming' consolidation — across ~30 stateful cognitive modules. 100% local.
- Storage
- SQLite + FTS5 (optional SQLCipher encryption) for entities and keyword search; USearch HNSW for vectors. Prediction-Error Gating decides whether new info is merged, superseded, or stored; FSRS-6 (21 parameters) governs natural decay so unused memories fade; an active-forgetting `suppress` tool applies reversible top-down inhibition without erasing. Default embeddings are Nomic Embed Text v1.5 (768→256d Matryoshka); Qwen3-0.6B optional.
- Retrieval
- A 7-stage cognitive search pipeline: HyDE query expansion + keyword + semantic + reranking (Jina Reranker v1 Turbo) + temporal + competition + spreading activation. 'Memory dreaming' replays recent memories to discover and persist new graph connections; `deep_reference` runs an 8-stage trust-scored reasoning pass with contradiction analysis.
- Self-host
- Self-host: trivial
- License
- AGPL-3.0
- Pricing
- Open-source AGPL-3.0, free to self-host (`npm install -g vestige-mcp-server`); first run downloads a ~130MB embedding model, then fully offline. No paid tier. · Free / OSS
- GitHub stars
- 565
- Last release
- 2026-06-19
- Last commit
- 2026-06-28
- First catalogued
- 2026-06-28
Strengths
- Cognitive-science memory model: FSRS-6 decay, prediction-error gating, spreading activation, synaptic tagging, and consolidation 'dreaming' — not a vector store with decay bolted on
- Single self-contained Rust binary, 100% local (SQLite+FTS5 + USearch HNSW, optional SQLCipher encryption), with a 25-tool MCP server across 8+ IDEs
- Active forgetting via a reversible `suppress` tool (top-down inhibition, 24h labile window) plus a real-time 3D memory dashboard
Watch out
- AGPL-3.0 copyleft: self-host freely, but offering Vestige as a network service requires open-sourcing your modifications — confirm license fit before commercial embedding
- Neuroscience mechanisms and retrieval gains are vendor-described, not independently benchmarked on a shared eval
- Single-maintainer project (~565 stars); some platform builds (Intel Mac, Windows MSVC+CUDA) need manual ONNX/toolchain steps
Best for
- Developers wanting a fully-local, inspectable cognitive memory for coding agents that decays, consolidates, and forgets like a brain
Benchmark results
No sourced results yet.
Sources
- Vestige README (vendor)
- GitHub API repo metadata (stars, AGPL-3.0 license, v2.1.27 release) (third-party)
Last verified 2026-06-28 · updated by discover-frameworks