Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.
| Date | Stars |
|---|---|
| 2026-07-24 | 1163 |
| 2026-07-25 | 1164 |
| 2026-07-28 | 1164 |
| 2026-07-30 | 1164 |
| 2026-07-31 | 1164 |
| 2026-08-06 | 1164 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="static/assets/auditpilot-logo.svg" width="108" alt="AuditPilot logo" /> </p> <h1 align="center">审脉 AuditPilot</h1> <p align="center"> 面向审计交付场景的企业级 AI Agent 工作台：把证据检索、工具执行、Harness 评测、人工复核与整改闭环放进同一条可追溯工作流。 </p> <p align="center"> <img alt="Python" src="https://img.shields.io/badge/Python-3.10%2B-3776AB?style=flat-square&logo=python&logoColor=white" /> <img alt="FastAPI" src="https://img.shields.io/badge/FastAPI-Agentic%20Backend-009688?style=flat-square&logo=fastapi&logoColor=white" /> <img alt="RAG" src="https://img.shields.io/badge/Agentic_RAG-Evidence_Grounded-0F766E?style=flat-square" /> <img alt="Evaluation" src="https://img.shields.io/badge/Eval_Harness-Release_Gate-2563EB?style=flat-square" /> <img alt="Secrets" src="https://img.shields.io/badge/Secrets-Not_Committed-10B981?style=flat-square" /> </p>  ## Why AuditPilot 很多 Agent 项目停留在聊天框或 Demo。AuditPilot 选择一个更“硬”的落地场景：企业审计交付。它需要证据、控制、风险、复核、报告和整改闭环，也天然要求可追溯、可回归、可解释。 AuditPilot 的目标不是替代审计师，而是把审计师反复执行的取证、映射、检查、补证和交付动作，组织成一套可治理的 Agent 工作流。 ## What it does | 模块 | 能力 | | --- | --- | | Audit Workspace | 审计立项、控制矩阵、审计程序、抽样计划、发现、整改和交付包。 | | Agent Runtime | 有界 Plan / Execute / Reflect 循环、步骤依赖、运行预算、任务产物、失败恢复和人工复核出口。 | | Agentic RAG | 知识写入、切块、检索、来源引用、证据质量门和缺证提示。 | | Skills / MCP-style Tools | 工具 Schema、权限声明、TTL 缓存、熔断器、调用日志和工具指标。 | | Memory | Working / Episodic / Profile Memory，保留多轮审计上下文。 | | Evaluation Harness | 对任务、循环、工具、证据、图谱、安全、记忆、交付和改进分别评测；关键断言失败直接阻断发布。 | | Evidence Graph | 连接任务、步骤、工具运行和产物，检查来源覆盖、断裂依赖与关键孤点。 | | Governed Improvement | 失败只沉淀为经验候选，通过回归评测和人工批准后才允许复用。 | | Episode & Observability | 隐私友好的任务轨迹包、标准语义字段、工具证据、安全门、失败归因、干预记录和完整性摘要。 | ## Screenshots | Audit workspace | Agent runtime | | --- | --- | |  |  | | Agent collaboration | Layered evaluation | | --- | --- | |  |  | <p align="center"> <img src="docs/screenshots/auditpilot-overview-mobile.png" width="360" alt="AuditPilot mobile overview" /> </p> ## Architecture ```text Audit request -> Hybrid Intent Router -> Working + Episodic + Profile Memory -> Planner / Evidence / Control / Risk / Compliance / Remediation Agents -> Bounded dependency-aware Agent Loop -> Agentic RAG + Evidence Graph + Skills / MCP-style Tools -> Safety Gate + Reflection + Human Review -> 9-layer Component Evaluation + Release Gate -> Delivery Package + Governed Experience Candidate ``` Design boundaries: - LLMs help with understanding, summarization and explanation. - Evidence gaps, quality gates, permissions, risk signals and delivery state stay auditable. - High-risk or low-confidence outputs are routed to evidence completion and human review. ## Quick start ```powershell python -m venv .venv .\.venv\Scripts\Activate.ps1 pip install -r requirements.txt Copy-Item config.env.example config.env python start.py ``` The system can run in deterministic fallback mode without model keys. Add an OpenAI-compatible provider only when you want LLM-enhanced analysis. ## Security Do not commit real API keys. - Put local secrets in `config.env`. - Use platform secrets for deployment. - `config.env`, `.env*`, runtime data, logs, model artifacts and local databases are ignored by Git. - Example config files use placeholders only. ## Validation ```powershell .\.venv\Scripts\python.exe -m compileall -q agents services rag web tests scripts .\.venv\Scripts\python.exe -m unittest discover -s tests -p "test_*.py" ``` Current tests cover intent routing, memory compaction, skill validation/cache, bounded runtime execution, component assertions, evidence lineage, governed experience reuse, evaluation regression, repository-bound Harness gating, quality diagnostics and global search. ## Project layout ```t
Excerpt of 4,988 characters
Read on GitHub
56
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d43e4f9f92001f59, topic:ai-agent, topic:multi-agent, readme:ai agent
matched fp:d43e4f9f92001f59, topic:rag, topic:knowledge-graph