# ZTE-AICloud/Co-Sight

Repository: https://github.com/ZTE-AICloud/Co-Sight
Canonical: https://ross.abutalabs.com/products/co-sight
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, aim, zte, aicloud
Last push: 2026-04-14T13:18:44+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 8, longevity 35
- inputs: {"age_days": 491, "days_push": 141, "days_rel": 488, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1008, forks 277 (observed 2026-08-28T04:03:12.687649+00:00)

## What it is
Co-Sight is an open-source Python framework from ZTE for building Manus-like autonomous AI agent systems that generate high-quality research reports using low-cost LLMs. It supports flexible private deployment for enterprises and individuals.

## Use cases
- build my own manus-like ai agent system
- generate industry research reports with llm agents
- self-host an open-source deep research agent
- create travel guides and news analysis reports automatically
- deploy a private ai report generation system
- run autonomous research agents with cheap llm models

## When to choose
- you want an open-source, self-hosted alternative to closed Manus-style platforms
- you need to generate polished research reports with low-cost models
- private deployment and data control are requirements
- you want a balance of cost, quality, and stability in agent frameworks

## When to avoid
- you need a fully managed commercial agent platform with vendor support
- your use case is simple chatbot conversations rather than multi-step research
- you require extensive third-party integrations beyond the supported toolset
- you need guaranteed enterprise SLAs

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference
- domain: large-language-models, artificial-intelligence
- platform: python, self-hosted
- tags: manus-like, deep-research, report-generation, autonomous-agents, open-source-agents, private-deployment, ai-agents, retrieval-augmented-generation, docker, web-server

## Member repositories
- ZTE-AICloud/Co-Sight (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:12.687649+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 2026-08-30T07:12:07.792314+00:00, confidence not recorded.
  - readme: https://github.com/ZTE-AICloud/Co-Sight (fetched 2026-08-28T04:03:12.687649+00:00, sha 212da362d4ac)
- Data as of 2026-08-30T08:39:29.467469+00:00.