| Name | ace-context-engineering JSON |
| Version |
0.1.1
JSON |
| download |
| home_page | None |
| Summary | Agentic Context Engineering (ACE) - Evolving contexts for self-improving language models |
| upload_time | 2025-10-24 08:44:48 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | MIT License
Copyright (c) 2025 Prashant Malge
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE. |
| keywords |
agentic-ai
ai
context-engineering
curation
llm
playbook
reflection
self-improving
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# ACE Context Engineering
[](https://badge.fury.io/py/ace-context-engineering)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
**Self-improving AI agents through evolving playbooks.** Wrap any LangChain agent with ACE to enable learning from experience without fine-tuning.
**Based on research:** [Agentic Context Engineering (Stanford/SambaNova, 2025)](http://arxiv.org/pdf/2510.04618)
---
## What is ACE?
ACE enables AI agents to **learn and improve** by accumulating strategies in a "playbook" - a knowledge base that grows smarter with each interaction.
### Key Benefits
- **+17% task performance** improvement
- **82% faster** adaptation to new domains
- **75% lower** computational cost vs fine-tuning
- **Zero model changes** - works with any LLM
---
## Installation
### Using pip
```bash
# Default (FAISS vector store)
pip install ace-context-engineering
# With ChromaDB support
pip install ace-context-engineering[chromadb]
```
### Using uv (Recommended)
```bash
# Default (FAISS vector store)
uv add ace-context-engineering
# With ChromaDB support
uv add ace-context-engineering[chromadb]
```
**Environment Setup:**
```bash
# Copy example environment file
cp .env.example .env
# Add your API key
echo "OPENAI_API_KEY=your-key-here" >> .env
```
---
## Quick Start
### 3-Step Integration
```python
from ace import ACEConfig, ACEAgent, PlaybookManager
from langchain.chat_models import init_chat_model
# 1. Configure ACE
config = ACEConfig(
playbook_name="my_app",
vector_store="faiss",
top_k=10
)
playbook = PlaybookManager(
playbook_dir=config.get_storage_path(),
vector_store=config.vector_store,
embedding_model=config.embedding_model
)
# 2. Wrap your agent
base_agent = init_chat_model("openai:gpt-4o-mini")
agent = ACEAgent(
base_agent,
playbook,
config,
auto_inject=True # Automatic context injection
)
# 3. Use normally - ACE handles context automatically!
response = agent.invoke([
{"role": "user", "content": "Process payment for order #12345"}
])
```
### Add Knowledge to Playbook
```python
# Add strategies manually
playbook.add_bullet(
content="Always validate order exists before processing payment",
section="Payment Processing"
)
playbook.add_bullet(
content="Log all failed transactions with error codes",
section="Error Handling"
)
```
### Learning from Feedback
```python
from ace import Reflector, Curator
# Initialize learning components
reflector = Reflector(
model=config.chat_model,
storage_path=config.get_storage_path()
)
curator = Curator(
playbook_manager=playbook,
storage_path=config.get_storage_path()
)
# Provide feedback
feedback = {
"rating": "positive",
"comment": "Payment processed successfully"
}
# Analyze and learn
insight = reflector.analyze_feedback(chat_data, feedback)
delta = curator.process_insights(insight, feedback_id)
curator.merge_delta(delta)
# Playbook automatically improves!
```
---
## Architecture
```
┌─────────────────┐
│ Your Agent │ ← Any LangChain agent
│ (Generator) │
└─────────┬───────┘
│
▼
┌─────────────────┐
│ ACEAgent │ ← Automatic context injection
│ Wrapper │
└─────────┬───────┘
│
▼
┌─────────────────┐
│ Playbook │ ← Semantic knowledge retrieval
│ Manager │
└─────────────────┘
▲
│
┌─────────────────┐
│ Reflector │ ← Analyzes feedback
│ + Curator │ ← Updates playbook
└─────────────────┘
```
### Components
| Component | Purpose | Uses LLM? |
|-----------|---------|-----------|
| **ACEAgent** | Wraps your agent, injects context | No |
| **PlaybookManager** | Stores & retrieves knowledge | No (embeddings only) |
| **Reflector** | Analyzes feedback, extracts insights | Yes |
| **Curator** | Updates playbook deterministically | No |
---
## Configuration
```python
from ace import ACEConfig
config = ACEConfig(
playbook_name="my_app", # Unique name for your app
vector_store="faiss", # or "chromadb"
storage_path="./.ace/playbooks", # Default: current directory
chat_model="openai:gpt-4o-mini", # Any LangChain model
embedding_model="openai:text-embedding-3-small",
temperature=0.3,
top_k=10, # Number of bullets to retrieve
deduplication_threshold=0.9 # Similarity threshold
)
```
### Storage Location
By default, ACE stores playbooks in `./.ace/playbooks/{playbook_name}/` (like `.venv`):
```
your-project/
.venv/ ← Virtual environment
.ace/ ← ACE storage
playbooks/
my_app/
faiss_index.bin
metadata.json
playbook.md
your_code.py
```
---
## Examples
Check the [`examples/`](./examples/) directory for complete examples:
- **[agent_with_create_agent.py](./examples/agent_with_create_agent.py)** - Using create_agent (LangChain 1.0)
- **[basic_usage.py](./examples/basic_usage.py)** - Wrap an agent with ACE (start here!)
- **[with_feedback.py](./examples/with_feedback.py)** - Complete learning cycle
- **[chromadb_usage.py](./examples/chromadb_usage.py)** - Using ChromaDB backend
- **[custom_prompts.py](./examples/custom_prompts.py)** - Customize Reflector prompts
- **[custom_top_k.py](./examples/custom_top_k.py)** - Configure top_k retrieval
- **[env_setup.py](./examples/env_setup.py)** - Environment configuration
- **[manual_control.py](./examples/manual_control.py)** - Fine-grained control
---
## Use Cases
### 1. Customer Support Agents
Learn optimal response patterns from customer feedback.
### 2. Code Generation
Accumulate best practices and common patterns.
### 3. Data Analysis
Build domain-specific analysis strategies.
### 4. Task Automation
Improve workflows based on execution results.
---
## Testing
```bash
# Run all tests
uv run pytest tests/ -v
# Run specific test suite
uv run pytest tests/test_e2e_learning.py -v -s
# Run with coverage
uv run pytest tests/ --cov=ace --cov-report=html
```
**All 31 tests passing**
---
## Performance
From the research paper (Stanford/SambaNova, 2025):
| Metric | Improvement |
|--------|-------------|
| Task Performance | **+17.0%** |
| Domain Adaptation | **+12.8%** |
| Adaptation Speed | **82.3% faster** |
| Computational Cost | **75.1% lower** |
---
## Contributing
Contributions are welcome! Please:
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
---
## Documentation
- **[Technical Documentation](./docs/)** - Implementation details
- **[Paper Alignment](./docs/ACE_PAPER_ALIGNMENT.md)** - Research paper verification
- **[Implementation Summary](./docs/IMPLEMENTATION_SUMMARY.md)** - Complete technical summary
---
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
---
## Acknowledgments
- **Research Paper:** [Agentic Context Engineering](http://arxiv.org/pdf/2510.04618) by Zhang et al. (Stanford/SambaNova, 2025)
- **Built with:** [LangChain](https://python.langchain.com/), [FAISS](https://github.com/facebookresearch/faiss), [ChromaDB](https://www.trychroma.com/)
---
## Contact
- **Author:** Prashant Malge
- **Email:** prashantmalge101@gmail.com
- **GitHub:** [@SuyodhanJ6](https://github.com/SuyodhanJ6)
- **Issues:** [GitHub Issues](https://github.com/SuyodhanJ6/ace-context-engineering/issues)
---
<p align="center">
<strong> Star this repo if you find it useful!</strong>
</p>
Raw data
{
"_id": null,
"home_page": null,
"name": "ace-context-engineering",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": "Prashant Malge <prashantmalge101@gmail.com>",
"keywords": "agentic-ai, ai, context-engineering, curation, llm, playbook, reflection, self-improving",
"author": null,
"author_email": "Prashant Malge <prashantmalge101@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/c9/a1/f6a93c5fe1f0ee62d42b7d4deee7af3cacf8da547332059cad374846af14/ace_context_engineering-0.1.1.tar.gz",
"platform": null,
"description": "# ACE Context Engineering\n\n[](https://badge.fury.io/py/ace-context-engineering)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n\n**Self-improving AI agents through evolving playbooks.** Wrap any LangChain agent with ACE to enable learning from experience without fine-tuning.\n\n **Based on research:** [Agentic Context Engineering (Stanford/SambaNova, 2025)](http://arxiv.org/pdf/2510.04618)\n\n---\n\n## What is ACE?\n\nACE enables AI agents to **learn and improve** by accumulating strategies in a \"playbook\" - a knowledge base that grows smarter with each interaction.\n\n### Key Benefits\n\n- **+17% task performance** improvement\n- **82% faster** adaptation to new domains \n- **75% lower** computational cost vs fine-tuning\n- **Zero model changes** - works with any LLM\n\n---\n\n## Installation\n\n### Using pip\n```bash\n# Default (FAISS vector store)\npip install ace-context-engineering\n\n# With ChromaDB support\npip install ace-context-engineering[chromadb]\n```\n\n### Using uv (Recommended)\n```bash\n# Default (FAISS vector store)\nuv add ace-context-engineering\n\n# With ChromaDB support\nuv add ace-context-engineering[chromadb]\n```\n\n**Environment Setup:**\n\n```bash\n# Copy example environment file\ncp .env.example .env\n\n# Add your API key\necho \"OPENAI_API_KEY=your-key-here\" >> .env\n```\n\n---\n\n## Quick Start\n\n### 3-Step Integration\n\n```python\nfrom ace import ACEConfig, ACEAgent, PlaybookManager\nfrom langchain.chat_models import init_chat_model\n\n# 1. Configure ACE\nconfig = ACEConfig(\n playbook_name=\"my_app\",\n vector_store=\"faiss\",\n top_k=10\n)\n\nplaybook = PlaybookManager(\n playbook_dir=config.get_storage_path(),\n vector_store=config.vector_store,\n embedding_model=config.embedding_model\n)\n\n# 2. Wrap your agent\nbase_agent = init_chat_model(\"openai:gpt-4o-mini\")\nagent = ACEAgent(\n base_agent,\n playbook,\n config,\n auto_inject=True # Automatic context injection\n)\n\n# 3. Use normally - ACE handles context automatically!\nresponse = agent.invoke([\n {\"role\": \"user\", \"content\": \"Process payment for order #12345\"}\n])\n```\n\n### Add Knowledge to Playbook\n\n```python\n# Add strategies manually\nplaybook.add_bullet(\n content=\"Always validate order exists before processing payment\",\n section=\"Payment Processing\"\n)\n\nplaybook.add_bullet(\n content=\"Log all failed transactions with error codes\",\n section=\"Error Handling\"\n)\n```\n\n### Learning from Feedback\n\n```python\nfrom ace import Reflector, Curator\n\n# Initialize learning components\nreflector = Reflector(\n model=config.chat_model,\n storage_path=config.get_storage_path()\n)\n\ncurator = Curator(\n playbook_manager=playbook,\n storage_path=config.get_storage_path()\n)\n\n# Provide feedback\nfeedback = {\n \"rating\": \"positive\",\n \"comment\": \"Payment processed successfully\"\n}\n\n# Analyze and learn\ninsight = reflector.analyze_feedback(chat_data, feedback)\ndelta = curator.process_insights(insight, feedback_id)\ncurator.merge_delta(delta)\n\n# Playbook automatically improves!\n```\n\n---\n\n## Architecture\n\n```\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Your Agent \u2502 \u2190 Any LangChain agent\n\u2502 (Generator) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n \u25bc\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 ACEAgent \u2502 \u2190 Automatic context injection\n\u2502 Wrapper \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n \u25bc\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Playbook \u2502 \u2190 Semantic knowledge retrieval\n\u2502 Manager \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u25b2\n \u2502\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Reflector \u2502 \u2190 Analyzes feedback\n\u2502 + Curator \u2502 \u2190 Updates playbook\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n```\n\n### Components\n\n| Component | Purpose | Uses LLM? |\n|-----------|---------|-----------|\n| **ACEAgent** | Wraps your agent, injects context | No |\n| **PlaybookManager** | Stores & retrieves knowledge | No (embeddings only) |\n| **Reflector** | Analyzes feedback, extracts insights | Yes |\n| **Curator** | Updates playbook deterministically | No |\n\n---\n\n## Configuration\n\n```python\nfrom ace import ACEConfig\n\nconfig = ACEConfig(\n playbook_name=\"my_app\", # Unique name for your app\n vector_store=\"faiss\", # or \"chromadb\"\n storage_path=\"./.ace/playbooks\", # Default: current directory\n chat_model=\"openai:gpt-4o-mini\", # Any LangChain model\n embedding_model=\"openai:text-embedding-3-small\",\n temperature=0.3,\n top_k=10, # Number of bullets to retrieve\n deduplication_threshold=0.9 # Similarity threshold\n)\n```\n\n### Storage Location\n\nBy default, ACE stores playbooks in `./.ace/playbooks/{playbook_name}/` (like `.venv`):\n\n```\nyour-project/\n .venv/ \u2190 Virtual environment\n .ace/ \u2190 ACE storage\n playbooks/\n my_app/\n faiss_index.bin\n metadata.json\n playbook.md\n your_code.py\n```\n\n---\n\n## Examples\n\nCheck the [`examples/`](./examples/) directory for complete examples:\n\n- **[agent_with_create_agent.py](./examples/agent_with_create_agent.py)** - Using create_agent (LangChain 1.0) \n- **[basic_usage.py](./examples/basic_usage.py)** - Wrap an agent with ACE (start here!)\n- **[with_feedback.py](./examples/with_feedback.py)** - Complete learning cycle\n- **[chromadb_usage.py](./examples/chromadb_usage.py)** - Using ChromaDB backend\n- **[custom_prompts.py](./examples/custom_prompts.py)** - Customize Reflector prompts\n- **[custom_top_k.py](./examples/custom_top_k.py)** - Configure top_k retrieval\n- **[env_setup.py](./examples/env_setup.py)** - Environment configuration\n- **[manual_control.py](./examples/manual_control.py)** - Fine-grained control\n\n---\n\n## Use Cases\n\n### 1. Customer Support Agents\nLearn optimal response patterns from customer feedback.\n\n### 2. Code Generation\nAccumulate best practices and common patterns.\n\n### 3. Data Analysis\nBuild domain-specific analysis strategies.\n\n### 4. Task Automation\nImprove workflows based on execution results.\n\n---\n\n## Testing\n\n```bash\n# Run all tests\nuv run pytest tests/ -v\n\n# Run specific test suite\nuv run pytest tests/test_e2e_learning.py -v -s\n\n# Run with coverage\nuv run pytest tests/ --cov=ace --cov-report=html\n```\n\n**All 31 tests passing** \n\n---\n\n## Performance\n\nFrom the research paper (Stanford/SambaNova, 2025):\n\n| Metric | Improvement |\n|--------|-------------|\n| Task Performance | **+17.0%** |\n| Domain Adaptation | **+12.8%** |\n| Adaptation Speed | **82.3% faster** |\n| Computational Cost | **75.1% lower** |\n\n---\n\n## Contributing\n\nContributions are welcome! Please:\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n---\n\n## Documentation\n\n- **[Technical Documentation](./docs/)** - Implementation details\n- **[Paper Alignment](./docs/ACE_PAPER_ALIGNMENT.md)** - Research paper verification\n- **[Implementation Summary](./docs/IMPLEMENTATION_SUMMARY.md)** - Complete technical summary\n\n---\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\n## Acknowledgments\n\n- **Research Paper:** [Agentic Context Engineering](http://arxiv.org/pdf/2510.04618) by Zhang et al. (Stanford/SambaNova, 2025)\n- **Built with:** [LangChain](https://python.langchain.com/), [FAISS](https://github.com/facebookresearch/faiss), [ChromaDB](https://www.trychroma.com/)\n\n---\n\n## Contact\n\n- **Author:** Prashant Malge\n- **Email:** prashantmalge101@gmail.com\n- **GitHub:** [@SuyodhanJ6](https://github.com/SuyodhanJ6)\n- **Issues:** [GitHub Issues](https://github.com/SuyodhanJ6/ace-context-engineering/issues)\n\n---\n\n<p align=\"center\">\n <strong> Star this repo if you find it useful!</strong>\n</p>\n",
"bugtrack_url": null,
"license": "MIT License\n \n Copyright (c) 2025 Prashant Malge\n \n Permission is hereby granted, free of charge, to any person obtaining a copy\n of this software and associated documentation files (the \"Software\"), to deal\n in the Software without restriction, including without limitation the rights\n to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n copies of the Software, and to permit persons to whom the Software is\n furnished to do so, subject to the following conditions:\n \n The above copyright notice and this permission notice shall be included in all\n copies or substantial portions of the Software.\n \n THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\n SOFTWARE.",
"summary": "Agentic Context Engineering (ACE) - Evolving contexts for self-improving language models",
"version": "0.1.1",
"project_urls": {
"Changelog": "https://github.com/SuyodhanJ6/ace-context-engineering/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/SuyodhanJ6/ace-context-engineering#readme",
"Homepage": "https://github.com/SuyodhanJ6/ace-context-engineering",
"Issues": "https://github.com/SuyodhanJ6/ace-context-engineering/issues",
"Repository": "https://github.com/SuyodhanJ6/ace-context-engineering.git"
},
"split_keywords": [
"agentic-ai",
" ai",
" context-engineering",
" curation",
" llm",
" playbook",
" reflection",
" self-improving"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "157afb0a398d57e1e6c522c3e14f33b7ce2f2c1fbbe4c7d0e5596d1aac0b4bd3",
"md5": "e80101db9ad64ce18d1124a54dc25b27",
"sha256": "ffb69cab375ba783f7a2f4f1125d86686c00cc7de38f97d806d114667281e010"
},
"downloads": -1,
"filename": "ace_context_engineering-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e80101db9ad64ce18d1124a54dc25b27",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 43158,
"upload_time": "2025-10-24T08:44:47",
"upload_time_iso_8601": "2025-10-24T08:44:47.216546Z",
"url": "https://files.pythonhosted.org/packages/15/7a/fb0a398d57e1e6c522c3e14f33b7ce2f2c1fbbe4c7d0e5596d1aac0b4bd3/ace_context_engineering-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "c9a1f6a93c5fe1f0ee62d42b7d4deee7af3cacf8da547332059cad374846af14",
"md5": "2e08bc28b181dfaf331a9f71b8ac00fd",
"sha256": "806853bc67df7f10d64be47b9121dedcce5325071a0a44f832b4b2bec23e0bbc"
},
"downloads": -1,
"filename": "ace_context_engineering-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "2e08bc28b181dfaf331a9f71b8ac00fd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 54880,
"upload_time": "2025-10-24T08:44:48",
"upload_time_iso_8601": "2025-10-24T08:44:48.672707Z",
"url": "https://files.pythonhosted.org/packages/c9/a1/f6a93c5fe1f0ee62d42b7d4deee7af3cacf8da547332059cad374846af14/ace_context_engineering-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-24 08:44:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "SuyodhanJ6",
"github_project": "ace-context-engineering",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "ace-context-engineering"
}
