Vestige

安装配置

{
    "mcpServers": {
        "vestige": {
            "command": "vestige-mcp"
        }
    }
}

README 摘要

# Vestige ### Local cognitive memory for MCP-compatible AI agents. [](https://github.com/samvallad33/vestige) [](https://github.com/samvallad33/vestige/releases/latest) [](https://github.com/samvallad33/vestige/actions) [](LICENSE) [](https://modelcontextprotocol.io) **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](#quick-start) | [Dashboard](#-3d-memory-dashboard) | [How It Works](#-the-cognitive-science-stack) | [Tools](#-25-mcp-tools) | [Docs](docs/) --- ## What's New in v2.1.23 "Receipt Lock Hardening" v2.1.23 turns the Sanhedrin Receipt Lock launch into something more portable, observable, and harder to spoof. - **Model-agnostic Sanhedrin presets.** Sanhedrin no longer guesses a large default verifier. Users choose any OpenAI-compatible endpoint/model, or start from custom, small laptop, Ollama, MLX, vLLM, llama.cpp, hosted API, or LiteLLM presets. - **Sharper Receipt Lock.** Verification claims inside code fences, quotes, blockquotes, or explicitly hedged "let me verify" language no longer trigger false vetoes, while actual "tests passed" claims still require command receipts. - **Safer command receipts.** Transcript command evidence now prefers structured tool-use receipts; loose JSON scanning is opt-in only. - **Visible fail-open telemetry.** Timeouts, unavailable model endpoints, and malformed verdicts are logged locally and surfaced in the dashboard's 7-day Sanhedrin stats. - **Durable evidence boundary.** Staged evidence remains useful context, but it cannot satisfy durable support or contradiction requirements by itself. - **Safer batch writes.** `smart_ingest` batch mode now keeps caller-separated items separate by default and returns merge previews when an existing memory is mutated. - **Opt-in NVIDIA acceleration path.** Qwen3 embedding builds expose CUDA/cuDNN feature flags for contributors and users with CUDA-capable hosts. ## 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. - **App...