Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 ai-governance Open-Source Projects
-
MLflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
Project mention: MLflow CVE-2026-64849: Cloud Credential Theft via Webhook SSRF | dev.to | 2026-08-20Original Source: MLflow Security Advisory / CISA
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
iFixAi
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
Project mention: iFixAi,open-source auditor that checks if your AI agent does its job | news.ycombinator.com | 2026-08-12 -
asqav-sdk
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
import { init, Agent } from "@asqav/sdk"; init({ apiKey: process.env.ASQAV_API_KEY }); const agent = await Agent.create({ name: "support-bot" }); await agent.startSession(); const sig = await agent.sign({ actionType: "stripe.refund", context: { amount: 1500, reason: "customer dispute" } }); console.log(sig.verificationUrl); // https://asqav.com/verify/sig_abc123 await agent.endSession({ status: "completed" });
-
Disciplined-AI-Software-Development
A disciplined methodology for AI-assisted software development. Covers architectural constraints, validation hooks, session governance, and PAG (Pattern Abstract Grammar) for structured AI collaboration. Copy claude-setup/ into your project to start.
-
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
-
GAAI-framework
Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.
Project mention: Show HN: GAAI – One agent plans, one codes. A Markdown folder governs both | news.ycombinator.com | 2026-03-12 -
diagnostic
iFixAi. The open-source diagnostic for AI misalignment. 32 tests across fabrication, manipulation, deception, unpredictability, and opacity. Provider-agnostic. Runs against OpenAI, Anthropic, Bedrock, Azure, Gemini, and more. Letter grade in under 5 minutes, content-addressed manifest for bit-identical replay. Built by iMe.
Project mention: Open-source diagnostic for Al misalignment. Model agnostic, industry agnostic | news.ycombinator.com | 2026-05-04 -
Kargo
Stop Scripting Promotions. Start Shipping with Kargo. Kargo automates promotion across dev, staging, and prod with approval gates and verification. Open source, built by the team behind Argo CD. Download now.
-
Project mention: Stop Giving Secrets to Your Workloads: From Long-Lived Credentials to Identity-Aware Egress | dev.to | 2026-03-17
If you are building infrastructure where workload identity and credential security matter, Warden is worth a look: https://github.com/stephnangue/warden
-
template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers (by AndrewAltimit)
Project mention: Template for secure AI multi-agent coding workflows | news.ycombinator.com | 2026-02-06 -
orloj
An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.
Project mention: We tried every multi-agent framework — then built our own runtime | dev.to | 2026-04-09Website: https://orloj.dev
-
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 -
halo-record
Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.
Some really good policies in there, at least inasmuch as they match up to what I have been thinking about. Was hoping for more implementation but the one package for attestation/ logging looks useful: https://github.com/bkuan001/halo-record
-
open-bias
Open Source Agent Alignment: Make your agents follow rules. One line of code to enforce, trace, and improve.
Project mention: Show HN: Open Bias – proxy that enforces agent behavior at runtime | news.ycombinator.com | 2026-04-28 -
Project mention: Show HN: AxonFlow, governing LLM and agent workflows | news.ycombinator.com | 2026-01-20
-
AI-Governance-Architecture
Claude Code best practices applied to application design. Interactive HLD/LLD visualizations, a DB-governed implementation example, and the same primitives as a runnable agent: the Governed Agent. LLM-agnostic, DB-governed, GDPR-ready.
Project mention: Show HN: AI Governance Architecture – DB-Governed, LLM-Agnostic, EU AI Act | news.ycombinator.com | 2026-03-05 -
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 -
boffin
Staff-engineer layer for AI coding agents: routes per-edit architectural constraints and requires verification. Not another AGENTS.md.
Project mention: Show HN: Boffin – Staff-engineer layer for AI coding agents | news.ycombinator.com | 2026-07-26 -
CORE
CORE is a governance runtime for autonomous AI systems. It enforces constitutional rules during execution, prevents governance bypass, and creates auditable authority chains for agent actions across operational domains. (by DariuszNewecki)
Project mention: Core – Deterministic governance rules for AI-generated code (pip installable) | news.ycombinator.com | 2026-06-29 -
ai-rpi-protocol
Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the workflow. Works with Cursor, VS Code, Claude Code, and Windsurf across Claude, GPT, Gemini, Grok, and DeepSeek.
Project mention: Open source protocol that improves AI code quality in any IDE | news.ycombinator.com | 2026-02-19It amplifies discipline. It does not replace judgment.
I have been using it to reduce rewrites, clarify intent, and make AI assisted work more predictable.
Curious how others building daily with AI think about guardrails like this.
https://github.com/MiguelAxcar/ai-rpi-protocol
-
Project mention: Gate: a deterministic PII boundary between your data and AI agents | dev.to | 2026-06-04
If you've been holding off on connecting your AI agent to a real data source — database, internal API, or MCP server — because "what the model sees" was a vibes-based decision, this is the layer that turns it into a config file. Try it, scan your schema, and share what you find. The repo is github.com/GaaraZhu/gate. The issue tracker is open. The license is MIT.
-
artguard
Open-source AI artifact scanner. Detect malicious agent skills, MCP servers, and IDE rule files before they run.
Project mention: Open-sourced a scanner for AI skills/hooks called 'artguard' | news.ycombinator.com | 2026-03-05 -
-
nenya
A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
Project mention: Show HN: Nenya – A lightweight, highly secure AI API Gateway/Proxy written in Go | news.ycombinator.com | 2026-06-12 -
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).
ai-governance discussion
ai-governance related posts
-
I tried to forge my own AI agent's audit log
-
I built an AI agent that forges its own tools mid-task — and asks first (open source, 60-second demo)
-
How to formally verify an agent governance framework with TLA+
-
Five Adversarial Reviews Told Me My Study Was Measuring a Fiction
-
I Asked an AI to Author the Same Policy Tests 50 Times. It Hit Every Boundary in 49 Valid Runs.
-
Linux of AI is an open-source ecosystem designed to help reduce AI vendor lockin
-
Show HN: Boffin – Staff-engineer layer for AI coding agents
-
A note from our sponsor - AppSignal
www.appsignal.com | 13 Sep 2026
Index
What are some of the best open-source ai-governance projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | MLflow | 27,904 |
| 2 | iFixAi | 14,200 |
| 3 | asqav-sdk | 508 |
| 4 | Disciplined-AI-Software-Development | 406 |
| 5 | verifywise | 350 |
| 6 | GAAI-framework | 160 |
| 7 | diagnostic | 160 |
| 8 | warden | 152 |
| 9 | template-repo | 131 |
| 10 | orloj | 121 |
| 11 | deterministic-agent-control-protocol | 88 |
| 12 | halo-record | 79 |
| 13 | open-bias | 71 |
| 14 | axonflow | 70 |
| 15 | AI-Governance-Architecture | 53 |
| 16 | MakerChecker | 52 |
| 17 | boffin | 38 |
| 18 | CORE | 38 |
| 19 | ai-rpi-protocol | 37 |
| 20 | gate | 36 |
| 21 | artguard | 32 |
| 22 | AI-DECLARATION.md | 31 |
| 23 | nenya | 28 |
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