auditable-ai

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

AI CAD 建模 Agent：一句话需求进来，调研、提问、出 BOM，逐件完成真实 CAD 建模并导出装配 STEP（参数化 BRep，不是图片或网格）；几何与碰撞检查不过关就不交付。Windows 封闭 Beta。An AI CAD modeling agent: real parametric geometry from a one-line brief, gated by geometry and interference checks.

Auditable offline edge intelligence for low-cost edge devices, with benchmark evidence and public board proof on ESP32-C3.

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, acceptance checks, and reproducible paired benchmarks.

An accountability layer for investment agents: thesis cards, prediction ledgers, stock screeners, and feedback loops.

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

I've always believed that the hardest problems in AI aren't technical; they're architectural. We keep building systems that can't explain themselves, can't prove their own integrity, can't handle uncertainty without either freezing or lying. And then we act surprised when we don't trust them.

Cellular traffic forecasting from a target cell's local history, with public model weights and transparent expert routing.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.

An experimental Application Object Model for helping LLM agents understand, reason about, and operate real apps.

A governance layer for autonomous AI agents, proven on a life: 30+ scheduled agents made auditable, self-healing, and human-gated by single-writer field ownership. Architecture and patterns, no personal data.

paceval is a high-performance mathematical runtime for deterministic AI and energy-efficient edge computing.

Toward controlled evolution of artificial intelligence through validated neural grafting.

Local-first AI agent platform with a Tauri desktop app and Rust CLI. Run governed tools, durable sessions, multi-agent workflows, modular packages, and one-shot effect permits.

🏆 Companion research environment to the ACM Vibe Science publication · EASE '26 / VibeX · DOI 10.1145/3816483.3816631 · Auditable, resumable AI-assisted research.

Evidence-chain memory for AI agents - verbatim-first, auditable, anti-fabrication. Tell your story once, recall it with proof. Local-first skill + MCP server for Claude, Codex and any MCP client.

Yucong Duan's research hub: DIKWP graphs, artificial consciousness, semantic mathematics, auditable AI, publications and reproducible open-source experiments.

Defensive preprint, governance, and threat model for DOORM Genmount WorldModel-OS — a governance-first architecture for auditable agentic reasoning.

KnowMesh / 知络: local-first knowledge asset compiler for auditable RAG, traceable citations, and maintainable document intelligence.