verifiable-ai 开源项目推荐（153 个）

sentient-agi /OML-1.0-Fingerprinting

通过指纹技术实现 OML 1.0：开放、可变现且忠诚的 AI

dapr /dapr-agents

Build durable, autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.

manojmallick /sigmap

AI编码会话令牌减少97%——零deps，31种语言，MCP服务器

sergezuber /FABULA-LLM-5

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.

HiveForensics-AI /knolo-core

The open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.

AOSSIE-Org /OpenVerifiableLLM

Local Fully Open, Open-Weight, Open-Data, Verifiable LLMs. Language models you can check yourself: every training step recomputable bit for bit.

rapiddweller /archkeel

Archkeel checks architecture boundaries and declared changes in AI-assisted code.

cryptoyasenka /crypto-signal-board

在 OpenGradient TEE 中验证的 AI 驱动加密货币交易信号。6 项技术指标 + LLM 宏观风险判定 + ONNX 波动率预测。Next.js 16 · React 19 · TypeScript · Tailwind CSS 4 · Binance API · onnxruntime

ai-verification-observatory /inference-proofs

Provable LLM inference measured on the same hardware: overhead against production serving, proving time, proof size and check time, and what one proof establishes.

diagridio /python-ai

Durable execution for AI agents in Python: make LangGraph, CrewAI, Pydantic AI, OpenAI Agents, Google ADK, Strands and more fault-tolerant with Dapr Workflows on Diagrid Catalyst. Crash-proof agents, no re-run LLM calls.

Kartik24Hulmukh /Kairo-Phantom

Offline, on-device AI desktop agent with a signed, independently-verifiable audit trail — runs sealed with zero verified network egress; every action is hash-chained and checkable offline. MIT · pre-launch.

diagridio /dotnet-ai

Durable execution for Microsoft Agent Framework agents in .NET, on Dapr Workflow and Diagrid Catalyst

selectess /fde-consultants-protocoles

FDE Consultants Protocoles — open-source Forward Deployed Engineer + DeepSCR protocol: turn any coding agent (Claude Code, Codex, Cursor) into a certifying engineer with verifiable AI Assurance Scores, MCP tools, and a public trust registry. Apache-2.0.

AbdelStark /ProvableWorldModel

A commit-and-audit proof system for deterministic, quantized inference of a JEPA-style world model (LeWorldModel)

ApiliumCode /aingle

The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.

BigBirdReturns /axm-genesis

The frozen cryptographic kernel of the AXM protocol. Signed, content-addressed knowledge shards with post-quantum signatures (ML-DSA-44) and mechanically enforced non-selective recording. The gold shard is the definition of correctness.

cryptoyasenka /opengradient-repo-scanner

AI-powered GitHub repo security analysis, verified on-chain via OpenGradient TEE

oneshot2001 /onvif-mcp

Governed MCP server for IP cameras (VAPIX + ONVIF SOAP): fail-closed per-agent policy, hash-chained signed receipts on every call — including denials. First reference producer for the AAR spec.

helixprojectai-code /HELIX-GLYPH-LANGUAGE-HGL-

This unified document integrates glyph specification, dictionary, error taxonomy, canonical taxonomy, grammar, resonance matrix, security/custody, and operational runbooks into one continuous, human-centric format.

mapleleaflatte03 /meridian

Run AI agents locally with built-in governance and verifiable proof. Loom + Kernel + Intelligence.