v0.1.4 Release

This release improves workflow orchestration, parameter validation, and overall compatibility.

Highlights

• Improved workflow execution and graph handling, with better compatibility across old and new workflow patterns.
• Added stronger validation for tool and action parameters through stricter JSON schema checks.
• Normalized LLM-generated parameter types to reduce runtime mismatches.
• Improved workflow task progression and completion handling.
• Added utility support for async and mixed sync/async execution paths.
• Updated docs, tutorials, and examples to reflect the latest workflow behavior.

v0.1.3 Release

Release Notes

This release focuses on the agent/tool-calling upgrade and provider compatibility improvements.

Highlights

• Refactored CustomizeAgent and CustomizeAction to support structured inputs/outputs, JSON Schema-backed parameters, and more robust tool orchestration.
• Added native function-calling support for providers that speak the OpenAI-style tool protocol, with a fallback prompt-based path for others.
• Improved OpenRouter support with prompt caching, provider-aware request shaping, and cache-write cost warnings.
• Updated examples to match the new agent scheme and refreshed OpenRouter-based usage.
• Expanded test coverage for agent configuration, tool calling, and OpenRouter request behavior.

Compatibility

• Backward compatibility for JSON schema and workflow generation is preserved where possible.
• Existing prompt-based tool calling still works for providers that do not support native tool calls.

v0.1.2 Release

Release Highlights

This release upgrades EvoAgentX core LLM provider support and improves structured output handling.

LLM Provider Updates

• Updated OpenAILLM and OpenRouterLLM to support sync/async generation, streaming usage tracking, and tool-call output formatting.
• Refactored AliyunLLM and SiliconFlowLLM to use OpenAI-compatible clients.
• Improved LiteLLM compatibility with OpenAI-style response and cost handling.
• Added streaming cost tracking via usage chunks where providers support it.
• Added fallback behavior for providers that do not return cost data.

Output Parsing and Schema Handling

• Added optional JSON schema auto-fix behavior in LLMOutputParser.
• Added stricter Parameter validation for JSON schema-backed object and array parameters.
• Simplified JSON/data parsing utilities and removed unsafe eval usage in typed parsing.

v0.1.1 Release

What’s Changed in v0.1.1

Highlights

• Enhanced prompt templating and structured output parsing with JSON Schema support.
• Fixed module serialization and config restoration issues for nested BaseModules.
• Improved async stability, stream output behavior, and model response handling.
• Added new tool integrations, including Exa search, Gmail toolkit, finance toolkit, and API converter support.
• Introduced MAP-Elites optimizer support with example usage.

v0.1.0 – Initial Release

🚀 EvoAgentX v0.1.0 Release Notes

We are excited to release EvoAgentX v0.1.0, the first official version of our self-evolving agent framework. EvoAgentX enables developers, researchers, and AI enthusiasts to build, evaluate, and evolve agentic workflows with ease.

This release introduces the foundation of the EvoAgentX ecosystem, including workflow orchestration, long-term memory agents, RAG integration, and agent toolkits.

⸻

✨ Highlights
• 🔧 Agentic Workflow Orchestration Engine
• 🧠 Long-Term and short-term Memory Agent (MemoryAgent)
• 📚 RAG (Retrieval-Augmented Generation) Integration
• Support for built-in tools and external tools (MCP, HTTP, CLI, etc.)
• Support for Human-in-the-loop

⸻

📦 Installation

You can install the latest version from GitHub Release:

pip install evoagentx

Or build from source:

git clone https://github.com/EvoAgentX/EvoAgentX.git
cd EvoAgentX
pip install .

📘 Documentation

Documentation is being actively developed at:
🔗 https://github.com/EvoAgentX/EvoAgentX/blob/main/docs

⸻

🙌 New Contributors

Thanks to the following contributors
@bitkira
@Bhaskar-scientist
@xyq116

🤝 Contributing

We welcome issues, feature requests, and pull requests!
Please see CONTRIBUTING.md for more details.

⸻

🔒 License

Source code in this repository is made available under the MIT License.