Emend
Open source agent learning platform

Open source AI agent self-improvement

Run Emend yourself to give AI agents local memory, online playbook learning, and retrieval-backed behavior improvement without retraining the model.

pip install emend-ai

OSS

emend local loop

1

Publish interactions

Send each user turn, agent response, correction, and outcome to the local Emend server.

2

Extract memory and playbooks

Emend turns durable user facts into profiles and behavioral lessons into user playbooks.

3

Retrieve learned context

Your agent searches profiles and playbooks before the next response, so feedback changes future behavior.

Why open source Emend

Agent self-improvement you can inspect, run, and adapt

Most agents repeat mistakes because corrections disappear after the current conversation. Emend keeps the learning loop outside the model: interactions become profiles, playbooks, and searchable context your agent can use next time.

Standalone self-hosting

Run the open-source package on your own machine or infrastructure with a local FastAPI backend.

Online learning loop

Keep publishing interactions and Emend learns from real corrections as they arrive.

Local storage by default

Start with local SQLite for development, then choose stronger storage when your deployment needs it.

Open implementation

Inspect the memory, extraction, and retrieval path instead of treating agent learning as a black box.

OSS vs Enterprise

Start standalone. Upgrade when operations matter.

The open-source package is built for self-hosted online learning. Emend Enterprise adds managed infrastructure, stronger storage modes, governance surfaces, and continuous offline optimization for playbooks.

Open source

Enterprise

Best fit
Local builds, prototypes, self-hosted agent memory, and teams that want full code visibility.
Production teams that want managed operations, stronger storage, admin workflows, and support.
Storage
Standalone storage with local SQLite as the default open-source setup.
Managed and enterprise-grade storage options, including Supabase and native Postgres modes.
Learning mode
Online learning from published interactions, profiles, and user playbooks.
Online learning plus continuous offline optimization for playbooks using historical outcome evidence.
Operations
You run, secure, monitor, and scale the service yourself.
Managed solutions, operational dashboards, admin controls, billing, and deployment support.
Implementation shape

A self-improving agent loop in a few calls

Install the open-source package, run the local backend, publish interactions, then retrieve learned context before future agent turns.

open-source-loop.py
from emend import InteractionData, EmendClient client = EmendClient(url_endpoint="http://localhost:8081") client.publish_interaction(    user_id="user_123",    interactions=[        InteractionData(role="User", content="I travel weekly."),        InteractionData(role="Agent", content="Try this bulky laptop."),        InteractionData(            role="User",            content="Too heavy. Prioritize battery life and weight.",        ),    ],    source="local-agent",    session_id="session_001",) context = client.search(    query="laptop recommendation for user_123",    user_id="user_123",)
Frequently asked questions

Open-source agent improvement, without the hand-waving

Open-source AI agent self-improvement is a feedback loop where an agent records real interactions, extracts useful memory and behavioral guidance, and retrieves that context before future responses. Emend provides this loop as an inspectable open-source package.

Build the local loop first.

If you want inspectable AI agent self-improvement today, start with the open-source quickstart. If you need managed storage, dashboards, or offline playbook optimization, explore Emend Enterprise.