Show HN: Open-source implementation of Stanford's self-learning agent framework

3 weeks ago 2

AI agents that get smarter with every task 🧠

Agentic Context Engine learns from your agent's successes and failures. Just plug in and watch your agents improve.

Star ⭐️ this repo if you find it useful!

pip install ace-framework

export OPENAI_API_KEY="your-api-key" # Or use Claude, Gemini, or 100+ other providers

3. Create Your First ACE Agent

from ace import LiteLLMClient, Generator, Reflector, Curator, Playbook # Initialize with any LLM client = LiteLLMClient(model="gpt-4o-mini") generator = Generator(client) reflector = Reflector(client) curator = Curator(client) playbook = Playbook() # Teach your agent through examples # (See examples/ folder for complete training patterns) # Now it can solve new problems with learned strategies result = generator.generate( question="What is 7*8?", context="", playbook=playbook ) print(result.final_answer) # Agent applies learned strategies

That's it! Your agent is now learning and improving. 🎉

Why Agentic Context Engine (ACE)?

AI agents make the same mistakes repeatedly.

ACE enables agents to learn from execution feedback: what works, what doesn't, and continuously improve.
No training data, no fine-tuning, just automatic improvement.

📈 20-35% Better Performance: Proven improvements on complex tasks
🧠 Self-Improving: Agents get smarter with each task
🔄 No Context Collapse: Preserves valuable knowledge over time
🚀 100+ LLM Providers: Works with OpenAI, Anthropic, Google, and more

🌊 The Seahorse Emoji Challenge

A challenge where LLMs often hallucinate that a seahorse emoji exists (it doesn't). Watch ACE learn from its own mistakes in real-time. This demo shows how ACE handles the infamous challenge!

In this example:

Round 1: The agent incorrectly outputs 🐴 (horse emoji)
Self-Reflection: ACE reflects without any external feedback
Round 2: With learned strategies from ACE, the agent successfully realizes there is no seahorse emoji

Try it yourself:

python examples/kayba_ace_test.py

How does Agentic Context Engine (ACE) work?

Based on the ACE research framework from Stanford & SambaNova.

ACE uses three specialized roles that work together:

🎯 Generator - Executes tasks using learned strategies from the playbook
🔍 Reflector - Analyzes what worked and what didn't after each execution
📝 Curator - Updates the playbook with new strategies based on reflection

ACE teaches your agent and internalises:

✅ Successes → Extract patterns that work
❌ Failures → Learn what to avoid
🔧 Tool usage → Discover which tools work best for which tasks
🎯 Edge cases → Remember rare scenarios and how to handle them

The magic happens in the Playbook—a living document of strategies that evolves with experience.
Key innovation: All learning happens in context through incremental updates—no fine-tuning, no training data, and complete transparency into what your agent learned.

--- config: look: neo theme: neutral --- flowchart LR Playbook[("`**📚 Playbook** (Evolving Context) •Strategy Bullets ✓ Helpful strategies ✗ Harmful patterns ○ Neutral observations`")] Start(["**📝Query** User prompt or question"]) --> Generator["**⚙️Generator** Executes task using playbook"] Generator --> Reflector Playbook -. Provides Context .-> Generator Environment["**🌍 Task Environment** Evaluates answer Provides feedback"] -- Feedback+ Optional Ground Truth --> Reflector Reflector["**🔍 Reflector** Analyzes and provides feedback what was helpful/harmful"] Reflector --> Curator["**📝 Curator** Produces improvement deltas"] Curator --> DeltaOps["**🔀Merger** Updates the playbook with deltas"] DeltaOps -- Incremental Updates --> Playbook Generator <--> Environment

# Basic installation pip install ace-framework # With LangChain support pip install ace-framework[langchain] # With all features pip install ace-framework[all] # Development pip install ace-framework[dev] # Development from source (contributors) git clone https://github.com/kayba-ai/agentic-context-engine cd agentic-context-engine pip install -r requirements.txt pip install -e .

ACE works with any LLM provider through LiteLLM:

# OpenAI client = LiteLLMClient(model="gpt-4o") # Anthropic Claude client = LiteLLMClient(model="claude-3-5-sonnet-20241022") # Google Gemini client = LiteLLMClient(model="gemini-pro") # Ollama (local) client = LiteLLMClient(model="ollama/llama2") # With fallbacks for reliability client = LiteLLMClient( model="gpt-4", fallbacks=["claude-3-haiku", "gpt-3.5-turbo"] )

Quick Start Guide - Get running in 5 minutes
API Reference - Complete API documentation
Examples - Ready-to-run code examples
Prompt Engineering - Advanced prompt techniques

We love contributions! Check out our Contributing Guide to get started.

Based on the ACE paper and inspired by Dynamic Cheatsheet.

If you use ACE in your research, please cite:

@article{zhang2024ace,title={Agentic Context Engineering},author={Zhang et al.},journal={arXiv:2510.04618},year={2024}}

⭐ Star this repo if you find it useful!
Built with ❤️ by Kayba and the open-source community.

Read Entire Article

Show HN: Open-source implementation of Stanford's self-learning agent framework

3. Create Your First ACE Agent

Why Agentic Context Engine (ACE)?

🌊 The Seahorse Emoji Challenge

How does Agentic Context Engine (ACE) work?

Related

Blog Discovery Requires Effort

Imperative to Relational

Benchmark for Agent Context Engineering (2025)