ufy2024/AuC

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1058 stars · 42 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AuC (Agents-ufy-Core) is a Python single-agent framework built on asyncio with a pluggable ReAct reasoning loop, LLM adapters, tiered tool permissions (L1/L2/L3), and observable event streams. It includes terminal and web UIs, MCP client support, sandboxed tooling, IM-based approvals, and Claude Code-style engineering discipline features like context slicing and project rules.

Use cases

• build a single AI agent with a ReAct reasoning loop in Python
• run a coding agent with sandboxed shell and file tools
• require human approval for dangerous agent operations via IM
• connect an agent to multiple LLM providers like OpenAI, Anthropic, and DeepSeek
• add MCP tool servers to an agent workflow
• evaluate agent behavior with deterministic eval suites in CI
• run agent tasks in isolated Docker containers with resource limits

When to choose

• you want a Python agent framework with fine-grained tool permission tiers and approval flows
• you need both terminal and web interfaces for interacting with an agent
• you want built-in evals, sandboxing, and security hardening out of the box
• you prefer Chinese-language role libraries and documentation

When to avoid

• you need a mature multi-agent orchestration framework rather than a single-agent core
• you want a framework with a large ecosystem and long track record
• you need non-Python language support

Facets

framework · maturity active

agent-framework llm-inference mcp chatbot developer-tools cli web-framework security large-language-models developer-tools self-hosted python cli cross-platform react-loop tool-permissions terminal-ui web-ui skill-library evals im-approval code-agent sandboxing ai-agents automation web-server docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ufy2024/AuC")