Integrations Overview

ACE provides runners for popular agentic frameworks. Each runner adds self-improving learning to an existing agent with minimal code changes.

Available Integrations

Runner	Framework	Input	Insight Level
ACELiteLLM	LiteLLM (100+ providers)	Questions	Micro
LangChain	LangChain Runnables	Chain inputs	Meso
BrowserUse	browser-use	Task strings	Meso
ClaudeCode	Claude Code CLI	Task strings	Meso
OpenClaw	OpenClaw transcripts	JSONL trace files	Meso
MCP Server	MCP (stdio)	Tool calls	Micro
Opik	Opik observability	—	Monitoring

The Pattern

All integration runners follow the same three-step pattern:

1. INJECT   — Add skillbook strategies to the agent's context
2. EXECUTE  — Run the external agent normally
3. LEARN    — Reflector + SkillManager update the skillbook

Quick Construction

Every runner offers a from_model() factory that builds ACE roles automatically:

from ace_next import BrowserUse, LangChain, ClaudeCode

# Browser automation
browser = BrowserUse.from_model(browser_llm=my_llm, ace_model="gpt-4o-mini")

# LangChain chain/agent
chain = LangChain.from_model(my_runnable, ace_model="gpt-4o-mini")

# Claude Code CLI
coder = ClaudeCode.from_model(working_dir="./project", ace_model="gpt-4o-mini")

Shared Features

All runners share these capabilities:

• Skillbook persistence — save() / load via skillbook_path
• Checkpointing — automatic saves during long runs
• Deduplication — prevent duplicate skills
• Background learning — wait=False for async learning
• Progress tracking — learning_stats property

Which Integration Should I Use?

• Building a Q&A or reasoning agent? Use ACELiteLLM
• Have an existing LangChain chain or agent? Use LangChain
• Automating browser tasks? Use BrowserUse
• Running coding tasks with Claude Code? Use ClaudeCode
• Want to monitor costs and traces? Add Opik
• Learning from OpenClaw session transcripts? Use OpenClaw
• Exposing ACE as an MCP tool provider? Use the MCP Server
• Using a different framework? See the Integration Guide to build a custom runner