Autoresearch Python Packages

schliff

Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies

configgle

Type-safe hierarchical experiment configuration using pure Python dataclass factories and dependency injection.

weco

Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other optimizable code.

etzchaim

A diagnosable brain for your LLM. Cognitive architecture in the SOAR/ACT-R/CLARION/LIDA lineage, for the LLM era. Apache 2.0.

autor3search

Autonomous AI-driven performance optimization for any Python repository

autocontext

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

evo-hq-cli

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

evo-hq-agent

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

trackinizer

Epistemological database for agent and human efforts, beliefs, and findings.

epires

An epistemic auto-research harness and governance engine.

priml

Strongly typed configurable building blocks for A/B testing ML research.

aideml

AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

arbor-agent

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

autor3search-python

Autonomous AI-driven performance optimization for any Python repository

autoctx

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

autocrucible

Autonomous experiment platform — let LLM agents optimize anything through iterative edit-evaluate loops

tracecore

Deterministic runtime for agent evaluation

scholaraio

Scholar All-In-One: A research infrastructure for AI agents

research-git

A new Git tool for researchers and developers to capture experiments and features as reusable semantic units, then let agents reapply, adapt, or safely remove them on today’s codebase — aka Agentic Git.

autoresearch-prompt-manager

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

thehutch

Observability, steering, and provenance dashboard for autonomous-research agents.

principia-ai

Local-first, cross-domain research framework for evidence-grounded idea generation.

marketing-agent-example

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

autoevolve

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining