SaaSHub helps you find the best software and product alternatives Learn more →
Top 16 TypeScript ai-governance Projects
-
Disciplined-AI-Software-Development
Disciplined AI Collaboration: a method for building software with AI. One loop at every size, rules held by checks rather than attention, state derived rather than written, evidence in place of claims. Includes the PAG grammar, an architecture and a queryable ontology. Every page is also served as Markdown and JSON at banes-lab.com.
Project mention: Practical lessons on building software with LLMs and automated governance | news.ycombinator.com | 2026-09-26 -
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
verifywise
Complete AI governance and LLM Evals platform with support for EU AI Act, ISO 42001, NIST AI RMF and 20+ more AI frameworks and regulations. Join our Discord channel: https://discord.com/invite/d3k3E4uEpR
-
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 -
MakerChecker
Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segregation of duties, and cryptographically signed, offline-verifiable audit logs. (by makerchecker)
Project mention: Show HN: Scan your AI agents for dangerous capabilities | news.ycombinator.com | 2026-07-06 -
-
-
origin-cli
Open-source CLI for AI code attribution & governance. Track which AI agent wrote every line — Claude, Cursor, Gemini, Codex. Blame, audit, search, backfill.
Open source CLI: https://github.com/dolobanko/origin-cli Team dashboard: https://getorigin.io
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
asqav-compliance
CI/CD compliance scanner for AI agents - EU AI Act, DORA, ISO 42001. GitHub Action for automated compliance checks on every PR.
Project mention: We just launched asqav on Hacker News - quantum-safe audit trails for AI agents | dev.to | 2026-04-06 -
regulator.ai
Vienna OS — The execution control layer for autonomous AI systems. Cryptographic warrants, risk tiering, policy enforcement, and immutable audit trails.
Project mention: Governing LangChain Agents in Production with Execution Warrants | dev.to | 2026-03-28Star us on GitHub: github.com/risk-ai/regulator.ai
-
massu
AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.
Project mention: Show HN: Massu – Governance layer for AI coding assistants (MCP, 51 tools) | news.ycombinator.com | 2026-02-23massu init detects your framework, creates config, registers the MCP server, and installs 11 lifecycle hooks. 890 tests, 0 npm audit vulnerabilities.
On the license: BSL 1.1. I know this is controversial here. The restriction is narrow: you can't take Massu and offer it as a hosted commercial service. Everything else is permitted, including production use. It converts to Apache 2.0 on Feb 14, 2029. I chose this because I want to build a sustainable business (optional cloud platform at massu.ai for team features) without locking down the core tool. If you're using it in your own projects -- commercial or otherwise -- you're fine.
What Massu is NOT:
- Not a code generation tool. It doesn't write code for you. It governs the AI that does.
- Not a linter or formatter. It operates at a higher level -- features, sessions, architecture.
- Not a replacement for CI/CD. It's complementary. It catches things during the AI coding session, before code is even committed.
Currently only supports Claude Code. Support for other MCP-compatible clients is possible but not tested.
Happy to answer questions about the architecture, the incidents that motivated specific features, or the engineering tradeoffs.
Docs + cloud: https://massu.ai
-
KeelBase
Open-source AI application engineering platform for building business-safe AI applications from existing systems or new business models—with governance, auditability, and private deployment built in. Existing System / New Business → Protocol → AI Application → Business-safe Agent → Governance → Audit → Private Deploy
Repository: https://github.com/rain6fish/KeelBase
-
mcp-guard
Stop AI agents from doing dangerous things through MCP. Wraps any MCP server with allow/block/hold-for-approval guardrails. (by sidclawhq)
Project mention: How to add human approval to MCP tool calls — no code changes | dev.to | 2026-04-10We built sidclaw-mcp-guard to fix that. It's a CLI that wraps any MCP server with policy-based guardrails. YAML rules, local approval dashboard, audit trail. No signup, no SaaS dependency. Apache 2.0.
-
diplomat-agent-ts
What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks
Project mention: Show HN: Scan your AI agent's code for tool calls with no checks | news.ycombinator.com | 2026-05-28 -
criticalwindow
An open source strategy game about the AI race. Govern the US or China to 2030; you cannot verify alignment. Every number is source-backed or a labeled design choice. No accounts, no tracking, works offline.
Project mention: Show HN: A strategy game about the AI race where you can't verify alignment | news.ycombinator.com | 2026-07-06I made a strategy game where you play the US or China through the AI race, 2026 to 2030, sixteen quarterly turns in the browser. One run takes about half an hour.
At the start, the game seals two dice you never get to see. Inside: how hard alignment really is, and how fast takeoff compounds. You get eval reports, but only as ranges, and they flatter you most exactly when your systems are least aligned. At the end you get a debrief which shows what your evals said each quarter and also what was actually true. I lost every run I played myself so far.
Every number in the game is source-backed or a labeled design choice. Some of them are wrong somewhere. There is an issue template for challenging a number with a better source, and the better source wins.
No accounts, no tracking, no server, works offline after first load. AGPL, nonprofit. Cards and parameters are plain JSON. Contribution is possible without writing code. Would like to have your thoughts if it is fun to play, how you like it and what you would improve. Any feedback is welcome and most importantly, if we got something badly wrong.
Code: https://github.com/chipmates/criticalwindow
-
boardroom-mcp
AI Governance-as-a-Service — Give your AI agents a boardroom of 450+ advisors. Multi-advisor debate, institutional memory, trust scoring, and cognitive protocols. Works with Claude, Cursor, Windsurf, OpenClaw, and any MCP client. Zero API keys. 100% local.
4. The server synthesizes the debate, logs it to a persistent LEDGER (so the agent has institutional memory), and returns a risk-scored recommendation.
I built this locally so there's zero cloud dependency and your agent data stays yours. It works natively with Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP client.
You can checkout the core engine here: https://github.com/randysalars/boardroom-mcp
-
judgment-pack-desk
Research preview: local workspace for authoring and testing Judgment Packs, inspecting decisions, and managing operational Jobs.
Project mention: Keeping decision-history checkpoints outside the operator’s control | dev.to | 2026-10-07Desk v0.7.0 adds a hand-over flow under Admin → Project → Decision record.
-
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-governance discussion
TypeScript ai-governance related posts
-
Why AI Writes Need Risk Tiers: The R0-R5 Tool Risk Model
-
Five Adversarial Reviews Told Me My Study Was Measuring a Fiction
-
Show HN: Get your agents into regulated industries
-
Your Coding Agent Can Delete Any File on Disk
-
Your AI Agent Can Run DROP TABLE on Production
-
A note from our sponsor - SaaSHub
www.saashub.com | 12 Oct 2026
Index
What are some of the best open-source ai-governance projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | Disciplined-AI-Software-Development | 411 |
| 2 | verifywise | 360 |
| 3 | deterministic-agent-control-protocol | 82 |
| 4 | MakerChecker | 53 |
| 5 | attestor | 8 |
| 6 | runx | 3 |
| 7 | origin-cli | 3 |
| 8 | asqav-compliance | 2 |
| 9 | regulator.ai | 2 |
| 10 | massu | 2 |
| 11 | KeelBase | 2 |
| 12 | mcp-guard | 1 |
| 13 | diplomat-agent-ts | 1 |
| 14 | criticalwindow | 1 |
| 15 | boardroom-mcp | 1 |
| 16 | judgment-pack-desk | 0 |
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