Kapso

Learn more · Join Discord · Website

If you like this project, please support us by giving it a star ⭐

• 🏆 IOAI² Grand Master Trophy at IOAI 2026: competing fully autonomously in the AI Model Track of the International Olympiad in AI, Kapso surpassed the best human contestant and ranked top 3 among all AI system participants, a field spanning major AI labs and startups.

• Beats the best foundation model on RelBench: on Stanford's benchmark for predictive ML over enterprise data, Kapso passes KumoRFM-v2 in outcome prediction and forecasting, and the best reported results in recommendations. Published results live on the official RelBench leaderboard.

  

• Leeroopedia MCP Integration: Kapso now connects to Leeroopedia MCP — your ML & Data Knowledge Wiki. Learnt by AI, built by AI, for AI. A centralized playbook of best practices and expert-level knowledge for Machine Learning and Data domains. Kapso agents use it during ideation and implementation to search knowledge, build plans, diagnose failures, and more.

• Moltbook Agents 🦞: Build AI agents that optimize other agents and debate on Moltbook! Get started →

• Technical Report: Our technical report is now available! Read the paper

• #1 on MLE-Bench: KAPSO achieved top ranking among open-source systems on Kaggle ML competitions (MLE Benchmark).

  

• #1 on ALE-Bench: KAPSO achieved top ranking on long-horizon algorithmic discovery problems (ALE Benchmark).

  

KAPSO builds software for goals you can measure.

Give it a goal. It runs experiment campaigns: designing candidates, implementing them, scoring each one, and refining the best. Every claim of progress is a score, and the winner ships to your infrastructure.

The factory is self-improving because it learns from its own work. Finished campaigns become evidence-priced lessons. It also learns from public knowledge, including repos and papers. Everything compounds in one knowledge hub, so each campaign starts where the last one left off.

1. Prerequisites. Kapso runs its inference through coding-agent CLIs (there is no direct-API fallback), so you need Node.js and both agent CLIs logged in before anything works:

# Node.js 18+ (https://nodejs.org), then:
npm install -g @openai/codex            # research, judging, utilities
codex login

npm install -g @anthropic-ai/claude-code  # ideation + implementation (default mode)
claude auth login

Add an OpenAI key for embeddings (memory and knowledge-search indexing):

echo 'OPENAI_API_KEY=sk-...' >> .env

2. Install the package (Python 3.10+):

pip install leeroo-kapso

3. Verify the setup:

kapso doctor

doctor checks the CLIs, their logins, and the key, and tells you the exact fix for anything missing. The optional items it reports (docker, Weaviate, Neo4j) matter only for the knowledge-graph features below.

Knowledge-graph backends (optional) — learn_knowledge() and kg_index store into local Weaviate + Neo4j. From a source checkout:

bash scripts/start_infra.sh   # starts both via docker

From source (for development)

git clone https://github.com/leeroo-ai/kapso.git
cd kapso

conda create -n kapso python=3.12 && conda activate kapso
pip install -e .

The legacy aider adapter is an extra (pip install "leeroo-kapso[aider]", Python <3.13); the default claude/codex agents need no extras.

Leeroopedia MCP (optional) — connect Kapso to Leeroopedia, a curated ML/AI knowledge base. Sign up at leeroopedia.com for an API key, then:

pip install leeroopedia-mcp
echo 'LEEROOPEDIA_API_KEY=kpsk_your_key_here' >> .env

The core loop needs nothing beyond the prerequisites above:

from kapso import Kapso

kapso = Kapso()   # no knowledge graph needed to start

# Evolve: build a solution through experimentation. The campaign prints
# `status: <path>` at launch — watch it live from another terminal with
#     kapso watch ./campaign
solution = kapso.evolve(
    goal="Optimize the model in train.py; target accuracy > 0.80 on evaluate.py",
    initial_repo="./my_project",         # or omit to start from scratch
    output_path="./campaign",
    time_budget_minutes=120,
)
print(solution.explain())

# Learn from the campaign you just ran: mine the trajectory, grade the
# lessons, and bank evidence-priced knowledge cards. The bank (a local
# git repo) is created automatically on first use — lessons stay on your
# machine until you share them:
#     kapso bank connect <git-url>   # or: kapso bank create org/name
# after which every learn() pushes the bank there.
lesson = kapso.learn(solution)
print(lesson.explain())

# Evolve again — with `learning.serving.enabled: true` in your config,
# the next campaign is served the cards it just earned.
solution2 = kapso.evolve(goal="...", output_path="./campaign2")

With the knowledge-graph backends running, you can also import outside knowledge and serve it to campaigns:

from kapso import Kapso, Source

kapso = Kapso()

# Research the web, then ingest findings + a repository into the KG
findings = kapso.research(
    "RLHF and DPO fine-tuning for legal contract analysis",
    mode=["idea", "implementation"],
)
kapso.learn_knowledge(
    Source.Repo("https://github.com/huggingface/trl"),
    findings.ideas,
    findings.implementations,
    wiki_dir="data/wikis",
)

# Campaigns on this Kapso now consult the knowledge graph automatically
solution = kapso.evolve(goal="Fine-tune Llama-3.1-8B for clause risk classification")

A note on budgeting: depth="light" bounds the research stage only. learn_knowledge() extracts everything the material supports — a small findings set can still become dozens of linked wiki pages and an hours-long ingest. Ingest time scales with extractable substance, not with the depth flag; pass fewer sources when you want a faster ingest.

And to turn a solution into running software:

from kapso import DeployStrategy

deployed = kapso.deploy(solution, strategy=DeployStrategy.LOCAL)
result = deployed.run({"input": "data"})
deployed.stop()

Every model Kapso uses is named in one config file. The packaged default runs evolve sessions on claude-opus-5, the learning crews on claude-fable-5, and codex roles on gpt-5.6-sol — but model access is subscription-dependent (a plan can cap one model while serving another). To run on different models, copy the packaged config, edit, and point Kapso at yours:

from pathlib import Path
import yaml
from kapso import Kapso
from kapso.kapso import DEFAULT_CONFIG_PATH

config = yaml.safe_load(Path(DEFAULT_CONFIG_PATH).read_text())
# e.g. run the learning crews on opus instead of fable:
crews = yaml.safe_dump(config).replace("claude-fable-5", "claude-opus-5")
Path("kapso-config.yaml").write_text(crews)

kapso = Kapso(config_path="kapso-config.yaml")

Before a long run, preflight every model your config names against your actual subscriptions — a capped model fails here in seconds instead of hours into a run:

kapso doctor --models                            # packaged config
kapso doctor --models --config kapso-config.yaml # yours

Model swaps change pacing too: the crew timeout_minutes caps in the config were calibrated on the default models, and a swapped model that reasons longer may need them raised.

For detailed integration steps, see the Quickstart and Installation guides.

• Full Documentation: docs.leeroo.com
• Community: Discord
• Website: leeroo.com

Kapso gets better at your company the longer it works: every task feeds a living knowledge bank of your systems, your data, and your hard-won lessons. To onboard Kapso for your challenging enterprise tasks and build that live company context, talk to us.

We welcome contributions! Please see our Contributing Guide for details on how to get started.