Vibe Coding Discover

AI Agents

FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence

★ 14013 forksPythonApache-2.0mikamikasuki

FOREST is an AI research agent that takes a project from literature review and hypothesis formation through code execution, experiment analysis, and paper drafting. Its editable research graph preserves decisions and links claims and figures to evidence.

Use Cases

Explore research directions and review scientific literatureGenerate hypotheses and design experiments with baselines and metricsWrite and run research code on local or remote computeAnalyze experimental results and revise research plansTrack claims, figures, and manuscript sections back to evidenceGenerate a research paper from project results

Built With

Language
Python
Frameworks
FastAPI · SQLAlchemy · scikit-learn

Tags

research-agent · scientific-research · autonomous-research · literature-review · hypothesis-generation · experiment-execution · evidence-tracking · paper-writing · research-graph · long-horizon-agents