aicoolies logo

AI Scientist v2

Autonomous scientific discovery via agentic tree search

Share
open-sourceOpen Source
Visit Website →

AI Scientist v2 is Sakana AI's open-source system for fully autonomous scientific research using LLM-powered agentic tree search. It generates hypotheses, designs experiments, writes and executes code, analyzes results, and produces publishable manuscripts without human intervention. The system uses progressive exploration with backtracking to navigate the research space efficiently.

AI Scientist v2 represents a new category of AI tooling — autonomous research agents that conduct the entire scientific discovery process end-to-end. Starting from a research topic or question, the system generates hypotheses, designs experimental protocols, writes the code needed to run experiments, executes those experiments, analyzes the results statistically, and produces a formatted manuscript ready for review. The agentic tree search approach means it can explore multiple research directions simultaneously and backtrack when a path proves unproductive.

The system builds on learnings from the original AI Scientist by Sakana AI, adding progressive exploration that manages compute budgets intelligently. Rather than committing fully to a single research direction, v2 allocates resources across promising branches and deepens investigation where results are most interesting. This mirrors how experienced researchers allocate their time — pursuing multiple leads while doubling down on the most promising findings.

With over 4,600 GitHub stars and an ICLR 2025 Workshop acceptance, AI Scientist v2 has gained attention from both ML researchers and developers interested in agentic system design patterns. The architecture patterns — tree search over complex task spaces, progressive resource allocation, and automated evaluation — are applicable beyond scientific research to any domain requiring systematic exploration. Sakana AI, backed by over $300M in funding, continues active development under a responsible AI research license.

Pricing

Free for research use — custom license terms

Platforms

Python — requires LLM API access for agent operation

Categories

Tags

Use Cases

Alternatives

CrewAI logo

CrewAI

Multi-agent AI framework

Python framework for orchestrating autonomous AI agents that collaborate to accomplish complex tasks. Define agents with specific roles, goals, and backstories, then organize them into crews with sequential or parallel task execution. Supports tool usage (web search, file I/O, API calls), memory, delegation between agents, and human-in-the-loop input. Works with OpenAI, Anthropic, local models, and more. 25K+ GitHub stars. Leading multi-agent framework alongside LangGraph and AutoGen.

open-sourceOpen Source
AutoGen logo

AutoGen

Microsoft's conversational multi-agent framework

AutoGen is an open-source programming framework from Microsoft Research for building AI agents and facilitating cooperation among multiple agents to solve complex tasks through multi-turn conversations. Pioneered conversable agents that interact, use tools, and involve humans in the loop for multi-agent workflows. v0.4 features a redesigned async event-driven architecture with stronger observability, flexible collaboration patterns, and reusable components.

open-sourceOpen Source
Composio logo

Composio

Tool infrastructure for AI agents

Composio connects AI agents to 1,000+ app toolkits with managed auth, delegated user connections, sessions, tool search, MCP gateway support, CLI workflows, and sandboxed workbench execution. It targets developers building Claude, Codex, Cursor, LangChain, CrewAI, OpenAI Agents SDK, and custom agent workflows that need authenticated business actions without hand-rolling every API integration.

freemiumOpen Source

Related Tools

Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source

Accomplish Coworker

Open-source desktop AI coworker for browsing and code execution.

Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.

open-sourceOpen SourceTelemetry

Headroom

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

open-sourceOpen SourceTelemetry

Codebase Memory MCP

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

open-sourceOpen SourceTelemetry
BeeAI Framework logo

BeeAI Framework

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

open-sourceOpen SourceTelemetry
Klavis AI logo

Klavis AI

MCP integration platform for agent tool use at scale

Klavis AI is an Apache-2.0 MCP integration platform for teams connecting AI agents to external SaaS tools and APIs. The public repo and official docs position it as infrastructure for reliable tool access at scale, so it fits teams that want reusable MCP connectors without treating every integration as a one-off script or custom OAuth maintenance project.

open-sourceOpen SourceTelemetry