# ResearAI/DeepScientist

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

Repository: https://github.com/ResearAI/DeepScientist
Canonical: https://ross.abutalabs.com/products/deepscientist
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-06-28T16:39:26+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 83, longevity 24
- inputs: {"age_days": 341, "days_push": 66, "days_rel": 112, "gap_med": 4, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3296, forks 329 (observed 2026-08-28T04:07:55.551542+00:00)

## What it is
DeepScientist is a local-first autonomous research studio that runs the full scientific research loop on your machine, from baselines and experiment rounds to paper-ready outputs. It integrates LLM coding agents (Codex, Claude Code, Kimi Code, OpenCode) with Findings Memory, Bayesian optimization, and a Research Map to iteratively drive experiments forward.

## Use cases
- run autonomous AI-driven scientific experiments locally
- automate the machine learning research loop from baseline to paper
- use LLM coding agents to conduct research projects
- optimize experiments with Bayesian optimization and findings memory
- generate paper-ready outputs from automated research
- manage research progress with one repo per quest and human takeover

## When to choose
- you want a self-hosted autonomous research agent that keeps the full experiment loop local
- you already use Codex, Claude Code, Kimi Code, or OpenCode and want them orchestrated for research
- you need visible, incremental research progress with human intervention at any point

## When to avoid
- you need a one-shot AI scientist that produces results without iterative experiment management
- you lack the local compute or API access required to run LLM coding agents
- you want a fully managed cloud research service rather than a local setup

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, machine-learning, workflow-automation, developer-tools
- domain: artificial-intelligence, data-science, developer-tools
- platform: python, cross-platform, self-hosted, cli
- tags: autonomous-research, ai-scientist, experiment-automation, bayesian-optimization, paper-writing, local-first, research-studio, agent-orchestration, ai-agents, research-automation

## Member repositories
- ResearAI/DeepScientist (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:55.551542+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 2026-08-29T18:42:58.152763+00:00, confidence not recorded.
  - readme: https://github.com/ResearAI/DeepScientist (fetched 2026-08-28T04:07:55.551542+00:00, sha 1ca61d269b60)
- Data as of 2026-08-30T08:39:29.467469+00:00.