Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 TypeScript ai-security Projects
-
Project mention: CyberStrike – open-source AI harness for offensive security (AGPL) | news.ycombinator.com | 2026-08-22
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
Project mention: I ran an AI pentester on a vibe-coded quiz app and found 22 vulnerabilities | news.ycombinator.com | 2026-04-07
-
emilia-protocol
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
Project mention: Two Independent CCS Implementations Achieve 14/14 Interoperability | dev.to | 2026-08-21EMILIA commit: https://github.com/emiliaprotocol/emilia-protocol/commit/5fb2eae9b20d17685e1ecbe061eb4ced03dbe64e
-
0
The multiplayer AI offensive security OS - open, self-improving, extensible. Find, verify, and fix vulnerabilities. (by 0sec-labs)
Project mention: Cybersecurity harness for full-stack LLM-driven penetration testing | news.ycombinator.com | 2026-09-29 -
agent-threat-rules
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
Project mention: I Scanned 2,386 MCP Packages on npm. 402 Were Critical. Here's What I Found. | dev.to | 2026-03-22Everything is open source (MIT): ATR rules + PanGuard scanner
-
ClawHub + SecureClaw. Install SecureClaw first, then use it to audit everything else.
-
node9-proxy
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Project mention: Vaults, Brokers, and Sandboxes: What Each One Stops, and What None of Them See | dev.to | 2026-09-29That is the layer node9 works at. It is not somewhere to keep secrets, and it does not replace a vault or a sandbox. It sits at a point in the sequence where the other three do not.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
toolhive-studio
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents
I ended up using their CLI and desktop app, ToolHive Studio. My hope was that ToolHive could become the control plane for running MCPs, storing auth, and distributing skills. Most importantly, I wanted one command that could register an MCP or skill across all of my coding agents.
-
mcp-observatory
CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.
Project mention: MCP Observatory: Scan, Test, and Secure MCP Servers Before Agents Depend on Them | dev.to | 2026-07-12MCP Observatory helps teams test, secure, and monitor MCP servers before agents depend on them.
-
defender
Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency. (by StackOneHQ)
Project mention: Show HN: Open-Source Lightweight Prompt Injection Safety | news.ycombinator.com | 2026-09-15 -
Project mention: Stop Sending Your .env to OpenAI: A Privacy Layer for OpenCode | dev.to | 2026-03-24
And it isn't destructive. Unlike regex scrubbing for analytics pipelines, this is fully reversible. Your data is abstracted during transit and restored for local execution. Nothing is lost (that's the whole point of Rehydra).
-
deterministic-agent-control-protocol
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.
Project mention: Show HN: DACP – governance gateway for AI coding agents | news.ycombinator.com | 2026-02-10 -
playground
A live environment to stress-test AI agent defenses through adversarial play 🧠 (by fabraix)
Project mention: Show HN: Open-source playground to red-team AI agents against public prompts | news.ycombinator.com | 2026-08-09 -
panguard-ai
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
Project mention: I Scanned 2,386 MCP Packages on npm. 402 Were Critical. Here's What I Found. | dev.to | 2026-03-22Everything is open source (MIT): ATR rules + PanGuard scanner
-
-
llm-fingerprint-detector
Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token Is Enough" (arXiv:2607.10252). Zero-dependency TypeScript library + CLI. Catches model substitution by resellers & gateways.
Project mention: Is That API Really Serving the Model It Claims? A Reproducible Fingerprint Test | dev.to | 2026-07-21git clone https://github.com/ToseaAI/llm-fingerprint-detector.git cd llm-fingerprint-detector npm install npm run build export LLM_FINGERPRINT_API_KEY='your-local-key' node dist/cli.js fingerprint \ --base-url https://your-endpoint.example.com/v1 \ --model your-model-id \ --out observed.json
-
agentshield-benchmark
Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance
Project mention: GentShield – Open benchmark of 6 AI agent security tools (537 test cases) | news.ycombinator.com | 2026-02-15 -
agent-chaperone
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Project mention: Show HN: Agent Chaperone – Screen AI agent tool calls and results with Jev | news.ycombinator.com | 2026-09-21 -
PROMPTPurify
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net
Project mention: PROMPTPurify: MB CPU-only prompt-injection guard (benchmarked vs. OSS guard) | news.ycombinator.com | 2026-05-29 -
sdk-javascript
The official JavaScript SDK for the Modzy Machine Learning Operations (MLOps) Platform.
-
Stroq
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.
Project mention: Show HN: Check your Claude Code, Codex and Cursor sessions for secrets | news.ycombinator.com | 2026-10-13 -
agent-shield
Multi-engine security scanner for AI agents, MCP servers & plugins — 13 engines, one report.
We built Agent Shield, a security scanner for AI agent tools, and used it to audit 17 of the most popular MCP servers — including official ones from Anthropic, AWS, Cloudflare, Docker, Brave, and Azure.
-
aegis
Credential isolation for AI agents. Local-first transparent proxy — your agent never sees your API keys. (by getaegis)
Project mention: How I Built Aegis — A Credential Isolation Proxy for AI Agents | dev.to | 2026-03-19The source is at github.com/getaegis/aegis — Apache 2.0 licensed. If this approach resonates, stars, issues, and feedback are genuinely helpful.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
TypeScript ai-security discussion
TypeScript ai-security related posts
-
Show HN: Check your Claude Code, Codex and Cursor sessions for secrets
-
Connect to Any MCP Server in TypeScript Over stdio and HTTP, Then List Its Tools
-
Show HN: Which of your secrets did your coding agent send?
-
M8M – See what your AI remembers about you and detect memory poisoning
-
Show HN: Open-source playground to red-team AI agents against public prompts
-
Show HN: We are giving away > over the next 12 months to hack AI agents
-
Logs are claims. Receipts are proofs.
-
A note from our sponsor - AppSignal
www.appsignal.com | 13 Oct 2026
Index
What are some of the best open-source ai-security projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | CyberStrike | 3,091 |
| 2 | numasec | 806 |
| 3 | emilia-protocol | 612 |
| 4 | 0 | 511 |
| 5 | agent-threat-rules | 408 |
| 6 | secureclaw | 347 |
| 7 | node9-proxy | 219 |
| 8 | toolhive-studio | 171 |
| 9 | mcp-observatory | 140 |
| 10 | defender | 126 |
| 11 | rehydra-sdk | 98 |
| 12 | deterministic-agent-control-protocol | 82 |
| 13 | playground | 76 |
| 14 | panguard-ai | 65 |
| 15 | prompt-injector | 33 |
| 16 | llm-fingerprint-detector | 36 |
| 17 | agentshield-benchmark | 27 |
| 18 | agent-chaperone | 22 |
| 19 | PROMPTPurify | 17 |
| 20 | sdk-javascript | 16 |
| 21 | Stroq | 16 |
| 22 | agent-shield | 15 |
| 23 | aegis | 14 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com