New in AI security
12 new repos on our list for this job.
Newest first. Growth cannot be measured yet, so they are listed separately. How we rank
New to our list
| Rank | Name |
|---|---|
| 1. | 0x45dd /pwner Autonomous agentic network penetration-testing tool (authorized use only) 82 stars+82 this week |
| 2. | Attention-Span-AI /Tego Tego limits what any AI agent can touch on Linux, and records every run. Rules for MCP servers, CI jobs, Python workers, 24/7 assistants and coding agents, enforced by the kernel. 13 stars+6 this week |
| 3. | CoWork-OS /CoWork-OS Rent the model. Own everything else. Free, open-source AI app for real work. 540 starsThis week: Not stated |
| 4. | dbx0 /executioner The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local. 136 stars+10 this week |
| 5. | guard-spec /guard-spec Self-hosted prompt-injection firewall for LLM apps. OpenAI-compatible gateway with rules, an ONNX classifier and embeddings, output guard, alerts, SSO. English and Vietnamese. 10 stars+10 this week |
| 6. | hevnsnt /CVEngine AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP integration. 697 stars+129 this week |
| 7. | lemonadesaltbagel /veil Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization. 154 stars+59 this week |
| 8. | N1nEmAn /sapper-v2 Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow. 1,699 stars+1,061 this week |
| 9. | onlyreadai /onlyread Make AI browser agents read-only: a Chrome extension that refuses writes (send, post, edit, delete) before they leave the browser. 22 starsThis week: Not stated |
| 10. | samvallad33 /vestige Think before doing, prove before saving. Vestige is the local-first cognitive operating system and deterministic safety kernel for autonomous AI agents. Powered by FSRS-6 causal graph memory, cryptographic Merkle-chained state ledgers, and out-of-band kernel gates bringing frontier PhD reasoning to local silicon with zero cloud token tax. 660 starsThis week: Not stated |
| 11. | sazabi /cve.now A free, public vulnerability feed: CVE, GHSA, OSV, CISA KEV and EPSS merged into one entry per vulnerability. RSS, JSON API and MCP. Docs and issues only. 138 stars+18 this week |
| 12. | SteelUnion /dsh-confirm-gate DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend. 101 stars+43 this week |