Tamper-proof memory + cryptographic audit trail for AI agents. HIPAA, SOC2, GDPR compliance built-in. Trust score for every response. Python & TypeScript SDKs. Rust-powered.
<div align="center">
<br/>
<img src="assets/logo.svg" alt="Connector OSS Logo" width="120" />
<br/>
# 🔐 Connector OSS — Make Every AI Decision Provable
### Your AI agents are making decisions. Can you prove what they did?
*Every AI decision deserves proof. We're building it.*
*Proof = CID content hash + HMAC-chained audit + Ed25519 signatures — verifiable by anyone outside your system.*
**Open-source AI agent framework with tamper-proof memory, cryptographic audit trail, and trust scoring. HIPAA, SOC2, GDPR, EU AI Act evidence-ready. Python, TypeScript, Docker.**
<br/>
[](https://github.com/GlobalSushrut/connector-oss/stargazers)
[](https://pypi.org/project/connector-agent-oss/)
[](https://www.npmjs.com/package/@connector_oss/connector)
[](https://hub.docker.com/r/adminumesh3011/connector-oss)
<br/>
[**Get Started**](#-get-started) · [**See It Work**](#-see-it-work) · [**Why Now**](#-why-now) · [**The Gap**](#-the-accountability-gap) · [**vs Others**](#-connector-vs-everything-else) · [**Docs**](docs/01_INDEX.md)
</div>
---
## 🚀 Get Started
```bash
pip install connector-agent-oss
```
```python
from connector_agent_oss import Connector
import os
c = Connector("deepseek", "deepseek-chat", os.environ["DEEPSEEK_API_KEY"])
result = c.agent("bot", "You are helpful").run("Hello!", "user:alice")
```
That's it. **3 lines.** Every response now includes:
- **`result.cid`** — tamper-proof content hash (CIDv1, SHA2-256)
- **`result.trust`** — kernel-verified trust score, 0–100
- **`result.audiHAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型