vestige
by samvallad33 (personal account)
Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, an append-only log, so you can see exactly what your agent did and why. (description from the project’s GitHub page)
Repository facts
- Stars
- 652
- Forks
- 72
- Open issues and pull requests
- 33
- Primary language
- Rust
- License
- GNU Affero General Public License v3.0 (AGPL-3.0)
- Owner
- samvallad33 · Personal account
- Created
- Jan 25, 2026
- Last push
- Oct 18, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 6,396: hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
930 starsPythonApache-2.0Last push Oct 18, 2026
Rank 8,680: secureagentics/Adrian
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
585 starsPythonApache-2.0Last push Sep 15, 2026
Rank 1,762: nolabs-ai/nono
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
4,560 starsRustApache-2.0Last push Oct 18, 2026
Rank 6,367: pipelab-org/pipelock
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits media…
937 starsGoApache-2.0Last push Oct 18, 2026
Rank 3,571: uber/ADR
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
2,064 starsPythonApache-2.0Last push Oct 16, 2026
Rank 4,243: kenryu42/cc-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports A…
1,664 starsTypeScriptMITLast push Oct 18, 2026