# InternScience/InternAgent

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Repository: https://github.com/InternScience/InternAgent
Canonical: https://ross.abutalabs.com/products/internagent
Homepage: https://discovery.intern-ai.org.cn/home
Language: Python
License: NOASSERTION
License Family: other
Topics: agentic-framework, ai-scientists, automatic-paper-survey, automatic-scientific-discovery, coding-agents, hypothesis-generation, llm-coder, multi-agent-systems
Last push: 2026-07-29T07:46:45+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 33
- inputs: {"age_days": 474, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1415, forks 127 (observed 2026-08-28T04:04:39.726189+00:00)

## What it is
InternAgent-1.5 is a Python-based unified agentic framework for long-horizon autonomous scientific discovery, orchestrating multi-agent systems that generate hypotheses, run experiments, and reproduce scientific papers. It supports end-to-end automation across physical, biology, earth, and life sciences, plus algorithm discovery and deep research capabilities.

## Use cases
- automate end-to-end scientific research from hypothesis to experiment
- generate and validate research hypotheses with LLM agents
- reproduce scientific papers autonomously
- run multi-agent deep research on complex questions
- discover and optimize algorithms automatically
- coordinate wet-lab and dry-lab experiment workflows
- build custom multi-agent pipelines for scientific tasks

## When to choose
- you need autonomous agents that run long-horizon scientific research workflows
- you want hypothesis generation, experiment execution, and paper reproduction in one framework
- you need multi-agent orchestration across scientific domains like biology or physics
- you want an open-source AI-scientist system with deep research integration

## When to avoid
- you need a simple single-agent chatbot or assistant
- your use case is general-purpose web or app development
- you require a lightweight agent framework with minimal dependencies
- you cannot provide LLM API keys or lack GPU/API resources for large-scale inference

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, machine-learning, rag, workflow-automation
- domain: artificial-intelligence, large-language-models, data-science
- platform: python, cross-platform
- tags: ai-scientist, autonomous-scientific-discovery, hypothesis-generation, multi-agent-systems, deep-research, paper-reproduction, long-horizon-agents, coding-agents, ai-agents, research-automation, linux, macos

## Member repositories
- InternScience/InternAgent (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:39.726189+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 2026-08-30T04:38:07.789637+00:00, confidence not recorded.
  - readme: https://github.com/InternScience/InternAgent (fetched 2026-08-28T04:04:39.726189+00:00, sha 25437546c9db)
  - homepage: https://discovery.intern-ai.org.cn/home (fetched 2026-08-29T11:51:04.063095+00:00, sha aaf8c7eea79c)
- Data as of 2026-08-30T08:39:29.467469+00:00.