# ufy2024/AuC

Agents-ufy-Core

Repository: https://github.com/ufy2024/AuC
Canonical: https://ross.abutalabs.com/products/auc
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-29T13:37:12+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 6
- inputs: {"age_days": 91, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1058, forks 42 (observed 2026-08-28T04:03:24.690309+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, chatbot, developer-tools, cli, web-framework, security
- domain: large-language-models, developer-tools, self-hosted
- platform: python, cli, cross-platform
- tags: react-loop, tool-permissions, terminal-ui, web-ui, skill-library, evals, im-approval, code-agent, sandboxing, ai-agents, automation, web-server, docker

## Member repositories
- ufy2024/AuC (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.690309+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:57:52.821347+00:00, confidence not recorded.
  - readme: https://github.com/ufy2024/AuC (fetched 2026-08-28T04:03:24.690309+00:00, sha 4c1c9acd6838)
- Data as of 2026-08-30T08:39:29.467469+00:00.