vestige
App Listed
Think before doing, prove before saving. Vestige is the local-first cognitive operating system and deterministic safety kernel for autonomous AI agents.
- Downloads
- 41
- Dependents
- Not applicable
- Stars
- 660
- Forks
- 73
- Contributors
- 17
- Commits
- 1,377
- Latest release
About
VESTIGE v6.2
The Ring-0 Autonomic Execution Kernel & World's First Causal Proof Engine for AI Agents
Think before doing. Prove before saving. Memory is root cause, not search.
Quick Start · Why We Ripped Out Vectors · S.T.R.A.T.A. Engine · The 6 MCP Verbs · Reflex Hooks · Vestige Operator
🚨 The Industry Lie: Memory Is Not a Search Engine
Every other AI memory tool on the market is a passive scrapbook built on unordered vector soup. Every other AI security tool is a stateless bouncer with complete amnesia.
When an autonomous coding agent breaks a build at 3:00 PM because a configuration flag was silently flipped at 9:00 AM, Vector RAG fails 100% of the time:
- The 3:00 PM stack trace (
ConnectionPoolExhaustedException) shares 0% semantic similarity with the 9:00 AM config edit (max_idle_time = 0). - Cosine similarity retrieves plausible-looking decoys instead of the causal ancestor.
- The agent guesses, edits the wrong file, fails again, and enters a $50,000 infinite retry loop.
Read the full README
Vestige v6.2 ends the guessing game. We ripped out ONNX, deleted vector embeddings, deleted keyword search, and deleted SQLite. In their place is a ~7.8 MB, 100% offline-verified Rust execution kernel that unifies pre-execution security gating, autonomic lifecycle hooks (reflex.sock), and backward causal credit assignment into a single closed-loop nervous system.
An Independent Study of 757 Agent Memory Systems (Agent Memory Atlas): "Every system in this atlas builds the ascent (extraction and retrieval). Almost none completes the descent (correction and forgetting)." Vestige is built for the descent.
⚡ Quick Start (30 Seconds)
One command installs the vestige-mcp Rust daemon, wires the 4 autonomic Reflex hooks into your IDE (Claude Code, Cursor, Codex, Windsurf, Gemini CLI), and replays your last 30 days of agent transcripts against our 114-rule gate to show every destructive command or failure loop Vestige would have stopped.
Operator is the guard for your agent's tool calls. npx @vestige/init --guard installs 102 STOP rules, OP-000 through OP-114, with OP-086–OP-097 and OP-100 reserved. It stops force pushes, dropped tables, recursive deletes, production deploys, credential reads and the rest of that closed list before they run, even when the command is disguised. Classification is deterministic: no model call and no network call. Operator Lite (numbered rules OP-000 through OP-025) is pinned beside the gate and judges every call too. An existing ~/.operator/gate/operator-gate.py is left in place.
npx @vestige/init
Verify your live cryptographic store and 6-tool surface at any time:
vestige precedent --query verify_log
🏛️ S.T.R.A.T.A. — The World's First Causal Proof Engine
The 102-rule gate is in this repository and is what --guard installs. See operator/README.md. board, letter, almost-forgot, onboard and briefing load companion modules when those files sit next to the gate. Buy Vestige Operator is the owner's copy of those companions: $149 once, every later version included, and a 30-day refund.
Underneath Vestige sits S.T.R.A.T.A. (Sequential Topological Reasoning for Autonomous Transaction Authorization)—an append-only, cryptographic execution ledger that replaces fuzzy similarity with mathematical provenance:
- Sequential (
BLAKE3+Ed25519): Every memory write, tool call, and gate stop is recorded as an immutable frame carrying theBLAKE3hash of the frame before it. Nightly segments are sealed withEd25519signatures. - Topological (
causal_walk): Memories are indexed by exact handles (id,tag,commit:<sha>, hunk-leveltouchedfile edges, and interned stack-trace symbols). Free-text guessing is refused—and on refusal, Handle Discovery automatically parses your query to return exact candidate handles found in your words. - Reasoning (
FSRS-6+Retroactive Salience Backfill):- FSRS-6 Decay (Precision Forgetting): Unverified, unreferenced session noise automatically decays out of working memory so context windows stay razor-sharp.
- Retroactive Salience Backfill (Runtime Credit Assignment): When a downstream failure or high-salience constraint lands, Vestige immediately walks the topological DAG backward on save, rescues the quiet upstream root-cause memory from FSRS-6 decay, boosts its salience, and writes a reversible cryptographic receipt.
- Autonomous (
reflex.sock): A zero-lock Unix Domain Socket (~/.vestige/reflex.sock) bridges external shell hooks directly into the hot in-memory Strata graph in <0.2ms—eliminating.serve.lockcontention across multiple concurrent IDE windows. - Transaction Authorization (
Operator+prove): Every agent action is treated as an untrusted transaction that must pass 114 pre-execution rules before running and can be verified post-fix via deterministic git-bisect test witnesses (causal_walk(action="prove")).
🧠 The Autonomic Dual-Tier Architecture
Standard MCP servers wait passively for an LLM to remember to call a tool. Vestige operates like a human nervous system: Reflex Hooks act as the spinal cord (firing automatically in 0 LLM turns and <0.2ms), while the 6 MCP Tools act as the deliberate prefrontal cortex.
┌────────────────────────────────────────┐
│ Model Prefrontal Cortex (6 Verbs) │
│ session · remember · recall · │
│ causal_walk · curate · precedent │
└──────────────────┬─────────────────────┘
│ stdio / JSON-RPC
▼
┌──────────────────────┐ Unix Domain Socket ┌────────────────────────────────────────┐
│ Reflex Hooks Engine │ ◄───────────────────► │ vestige-mcp Server Daemon │
│ (Spinal Cord) │ ~/.vestige/reflex.sock│ ┌───────────────────────────────────┐ │
│ │ (<0.2ms Zero-Lock) │ │ In-Memory Strata Graph (Hot RAM) │ │
│ • SessionStart │ │ │ • FSRS-6 scheduler state │ │
│ • PreToolUse (114) │ │ │ • Exact Handle & Symbol Index │ │
│ • PostToolUse (RSB) │ │ │ • Causal DAG & Backfill Engine │ │
│ • PreCommit (Prove) │ │ └─────────────────┬─────────────────┘ │
└──────────────────────┘ │ Exclusive Write Lock
▼
┌────────────────────────┐
│ Append-Only Strata Log │
│ (BLAKE3 + Ed25519) │
└────────────────────────┘
⚡ The 4 Autonomic Reflex Arcs (0-Turn Cognitive Injection)
Reflex::SessionStart(Active Handle Map Injection): On boot, resume, or context compaction, Vestige queries the local Git index against the hot Strata graph and injects the Top 5 Hot Entity Handles (id,tag,last_touched_file, and FSRS-6 retrievability) plus pinned repo rules. Your agent starts Turn 1 already holding the exact handles it needs.Reflex::PreToolUse(114 Gate Rules + Landmine Interception): BeforeBash,Edit, orWriteexecutes, Vestige runs 114 deterministic security rules (catching obfuscated shell commands,r''m,$IFS, ANSI-C quoting, base64 pipes, destructive SQL/git, and multi-step credential exfiltration) AND checks if the target file is linked to an un-recalledfailurenode in Strata. If a landmine exists, Reflex warns the agent with the exacthandle(mem-xxxx) before it repeats a mistake.Reflex::PostToolUse(Auto-Failure Capture + Inline Backfill): Whenever a command exits withexit_code != 0, Reflex automatically records a signedfailureframe in Strata, triggers Retroactive Salience Backfill across upstream touched nodes, surfaces any fadedforgotten_lesson(retrievability < 0.5), and appends the exactcausal_walkcommand directly to the tool output.Reflex::PreCommit(Proof-Carrying PR Enforcement): When an agent runsgit commitorgh pr createafter a logged failure in the current trajectory, Reflex verifies that a cryptographically signedprovebisect witness exists for the fix.
🛠️ The 6-Verb MCP Surface
Most MCP servers drown agents in 18–30 overlapping tool schemas—burning ~2,500 prompt tokens per turn and confusing smaller models. In v6.2, Vestige compresses its entire capability set into 6 flat-JSON cognitive verbs (while preserving internal backward-compatible aliases for all 18 legacy tool names):
| MCP Tool | Cognitive Intent | Key Actions & Capabilities |
|---|---|---|
1. session | Boot, Plan & Project | action: "start" | "status" | "set_intention" | "check_intentions" | "complete_intention" | "project"Manages cross-session prospective intentions, store health/stats, and compiles lock-free CLAUDE.md / AGENTS.md context fences directly from RAM. |
2. remember | The Single Gated Write | Flat parameters: content, tags, repo_path, files, is_decision.Automatically anchors codebase records when repo_path/files are present, runs inline Retroactive Salience Backfill (returning backfilled_handles), and auto-updates CLAUDE.md when tagged "pinned". |
3. recall | Exact-Handle Read | Flat parameters: handle, detail_level, query.Resolves exact IDs, prefixes, tags, or repo context ( get_context). Returns structured discovered_handles: [...] if free text is passed so the agent self-corrects on the immediate next turn. |
4. causal_walk | Root Cause & Bisect Proof | action: "walk" | "prove", from_handle, good_ref, bad_ref, test_cmd.• "walk": Auto-gathers GitHub issue/PR windows, walks hunk-level touched and git log -L ancestry backward, and auto-attaches faded forgotten_lesson nodes.• "prove": Executes a frozen-protocol git bisect against test_cmd and writes a signed Strata witness card. |
5. curate | Graph & State Mutation | action: "promote" | "demote" | "edit" | "link" | "bridge" | "connect_identities" | "suppress"Adjusts FSRS-6 stability weights, wires explicit causal links, bridges cross-project structural similarities ( ghostlink), joins shared entity identities, or permanently suppresses invalid records with a signed audit receipt. |
6. precedent | Receipts & Integrity Audit | query: "stops" | "receipt" | "replay" | "verify_log" | "scan_secrets" | "selftest"Inspects Operator gate stops, replays write receipts, scans for credential-shaped strings, and runs live BLAKE3 + Ed25519 verification ( strata-verify) without stopping the server. |
🏎️ David vs. Goliath: Making Local 8B Models Overpower Cloud Giants
Cloud memory wrappers charge a ~6,900-token tax per turn to stuff noisy vector chunks into frontier models. Because Vestige v6.2 pushes execution safety, failure detection, and backward credit assignment into a sub-millisecond local Rust daemon:
- Zero Context Stuffing: Exact handles and FSRS-6 decay keep active context lean (<200 tokens of memory overhead), preventing small-model attention degradation.
- Flat 6-Verb Schemas: Eliminates tool-selection hallucinations in 8B–9B local coding models (Qwen3-Coder-8B, Llama-3.1-8B, Gemma 4).
- $0.00 Cloud Token Tax: A release build of
vestige-mcpis verified in CI to never linkreqwest—guaranteeing zero network calls, zero telemetry, and zero API fees.
Run the 3-lane ablation benchmark (Mode A: Baseline vs. Mode B: Forward-Only FSRS-6 vs. Mode C: Full Vestige v6.2 with RSB + Reflex) and generate an Ed25519-sealed proof log:
./benchmarks/run-all-benchmarks.sh --ablation
🖥️ Host-Boundary CLI & Local WebGPU Dashboard
Because vestige-mcp routes concurrent CLI and hook calls through ~/.vestige/reflex.sock, you never hit .serve.lock collisions while an agent is active. The host CLI is stripped down to pure boundary operations:
vestige serve # Start the MCP server + reflex.sock IPC daemon
vestige backup <target-dir> # Seal active Strata segment with Ed25519 & write owner-only backup
vestige dashboard # Launch the loopback-hardened local UI on http://127.0.0.1:3927
vestige update # Verify .sha256 release digests and update binary
🛡️ Vestige Operator
- Vestige Core & Operator Lite (AGPL-3.0-only): Free and open-source forever. Includes the full Strata engine, the 6 MCP tools, the 4 Reflex hooks, and the built-in pre-execution rule gate.
- Vestige Operator ($149 One-Time License): Adds custom repository law authoring (
vestige.toml), team-wide proof-carrying PR enforcement (actions/proof-carrying-pr), multi-step exfiltration chain governors, and the weekly executive stop-board.
📚 Technical Reports & Documentation
- TR-2026-01: Retroactive Salience Backfill & Silent Rotation Benchmark — How inline runtime credit assignment + FSRS-6 solves delayed root-cause attribution.
- Configuration & Security Model — Loopback DNS-rebinding defenses, Sec-Fetch-Site enforcement, BLAKE3 frame chaining, and reflex.sock permissions (0o600).
- Getting Started Guide & FAQ — GETTING-STARTED.md · FAQ.md · UPGRADING.md
Built from first principles in Rust by Sam Valladares.
Zero vectors. Zero cloud tax. 100% causal proof.
Compatibility
- License
- AGPL-3.0
- Crate facts
- Not measured
- Runs on, Native code and Python bindings read crates on crates.io. This entry lists no crate.
Compare with similar projects
Order: strongest tier first, then most downloads, then name, with unmeasured values last. A library counts downloads over 30 days. An app counts binary downloads per release. An app with none counts its crate downloads over 30 days. ML Rust runs this catalogue, so its closest project always gets a row.
| Project | Downloads | Dependents | Stars | Latest release | Runs on (GPU) | Native code | License |
|---|---|---|---|---|---|---|---|
|
Think before doing, prove before saving. Vestige is the local-first cognitive operating system and deterministic safety kernel for autonomous AI agents. |
41 binary downloads per release | Not applicable | 660 | Not measured | Not measured | AGPL-3.0 | |
|
agent-client-protocol Featured
Core protocol types and traits for the Agent Client Protocol |
941,949 downloads over 30 days | 145 | 245 | 5.0.0 | GPU support unknown | No native code found | Apache-2.0 |
|
cortex-mem Listed
🧠 The production-ready cognitive foundation for autonomous systems such as Embodied-AI and OpenClaw. For memory management, from extraction and search to automated optimization, with SKILL, CLI, API, MCP, and insights dashboard out-of-the-box. |
126 downloads over 30 days | 6 | 318 | 2.7.0 | GPU support unknown | No native code found | MIT |
|
The autonomous, self-improving AI agent. Single Rust binary. Every channel. Recommended: the 40MB prebuilt binary for macOS, Linux and Windows: https://github.com/opencrabs/opencrabs/releases |
125 binary downloads per release | Not applicable | 1,027 | 0.5.15 | GPU support unknown | Binds native code: libsqlite3-sys, llama-cpp-sys-2, opusic-sys (feature local-tts), tree-sitter (feature code-graph), alsa-sys (feature local-stt) and 1 more | MIT |
|
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper. |
18 binary downloads per release | Not applicable | 483 | Not measured | Not measured | Apache-2.0 | |
|
shodh-memory Listed
Persistent cognitive memory for AI agents and robots — Hebbian learning, knowledge graph, spatial recall. Zenoh/ROS2 native. Single binary, runs offline. Python bindings |
1 downloads over 30 days | 0 | 322 | 0.2.0 | GPU support unknown | Binds native code: libmimalloc-sys, librocksdb-sys, lz4-sys, ort-sys, pnet_sys (feature zenoh) | Apache-2.0 |
|
An open protocol that gives AI agents a secure, sandboxed place to run code and use tools — with lean context usage. AXP works alongside MCP |
Not measured | Not applicable | 3 | Not measured | Not measured | Not measured | Apache-2.0 |
Why ListedNo archive, New or Featured rule places it, so it is Listed.
What it lacks for Featured
- The check holds no value for Homebrew installs on request over 365 days, Docker pull growth over 90 days. A gate that lacks its signal does not pass.
What else the check found
- The last activity is on 6 Nov 2026, 3 days ago. The rules expect an update within 365 days. Dormancy rule
Not measured: First release, Homebrew installs on request over 365 days, Docker pull growth over 90 days.
Exact rules: Listed, Featured app. The check on applied thresholds version 9.
Every rule outcome, as the check records it
expected-interval: app: E = 365 daysdormancy: last activity 2026-11-06, 3 days ago, E = 365: activefeatured: not featured: unknown homebrew_on_request_365d, docker_pull_growth_90dlisted: listed: no archive, new or featured rule applies
Measurements and sources
Each signal row shows the raw value, its source and the fetch date. The Sources list gathers every distinct source on this page. Movement needs more history.
Sources5 sources
- Description: the GitHub repository description
- GitHub releases, fetched
- GitHub repository, fetched
- Repology project, fetched
- GitHub contributors, fetched
Adoption41 binary downloads per release4 not measured
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| Active dependents | Not measured | Yes | ||
| New dependents (365 days) | Not measured | Yes | ||
| Peak active dependents | Not measured | Yes | ||
| Active dependents as a share of the peak | Not measured | Yes | ||
| Binary downloads per release | 41 | GitHub releases | Yes |
MaintenanceLatest human commit: 3 days ago7 not measured
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| Latest human commit | 2026-11-06 | GitHub repository | Yes | |
| Latest release | 2026-11-03 | GitHub releases | Yes | |
| First release | Not measured | Yes | ||
| Latest version | Not measured | Yes | ||
| Days the oldest outside issue waits for a reply | 0 | GitHub repository | Yes | |
| Maintainer replies over 365 days | 6 | GitHub repository | Yes | |
| Repository archived | false | GitHub repository | Yes | |
| Repository gone | false | GitHub repository | Yes | |
| Release commit or manifest in the repo | Not measured | Yes | ||
| Published docs | Not measured | Yes | ||
| Latest release fails cargo check | Not measured | Yes | ||
| Build check date | Not measured | Yes | ||
| Build check toolchain | Not measured | Yes |
SecurityNot measured
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| Unpatched vulnerabilities past the grace window | Not measured | Yes | ||
| RustSec unmaintained advisory | Not measured | Yes | ||
| Deprecation notice | Not measured | Yes | ||
| Deprecated requirement | Not measured | Yes |
Distribution125 binary downloads over the last 3 releases9 not measured
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| Releases | Not measured | Yes | ||
| Downloads over 30 days | Not measured | Yes | ||
| Binary downloads over the last 3 releases | 125 | GitHub releases | Yes | |
| Homebrew installs on request over 365 days | Not measured | Yes | ||
| Repology repository families | 1 | Repology project | Yes | |
| Docker pull growth over 90 days | Not measured | Yes | ||
| Docker pulls at the growth baseline | Not measured | Yes | ||
| Every version a prerelease | Not measured | Yes | ||
| Every version 0.0.x | Not measured | Yes | ||
| Every version yanked | Not measured | Yes | ||
| Crate deleted from crates.io | Not measured | Yes |
Repository660 stars, 73 forks, 17 contributors, 1,377 commits. Stars alone never qualify a project.1 not measured
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| GitHub stars | 660 | GitHub repository | Yes — one part of the repository route | |
| GitHub forks | 73 | GitHub repository | Yes — one part of the repository route | |
| Contributors with a GitHub account | 17 | GitHub contributors | Yes — one part of the repository route | |
| Commits on the default branch | 1377 | GitHub repository | No | |
| Repository's main crate left out of the entry | Not measured | Yes |
Facts that never count
| Signal | Value | Source | Fetched | Counts |
|---|---|---|---|---|
| License | AGPL-3.0 | GitHub repository | No | |
| Runs on, from listed crates and their direct dependencies | Not measured | No | ||
| What shows each backend | Not measured | No | ||
| Native code, from listed crates and their dependencies | Not measured | No | ||
| Python bindings, from direct dependencies of listed crates | Not measured | No | ||
| Crates that depend on a listed crate directly | Not measured | No |
Corrections and review history
No correction applies to this entry.
Judgments
A judgment enters only through an approved issue and a merged pull request.
No judgment applies to this entry.