LightAgent

LightAgent is an ultra‑lightweight, open‑source framework that now natively supports Skills — letting you compose reusable capabilities with persistent memory, tool use, and tree‑of‑thought reasoning. It streamlines multi‑agent collaboration (build self‑learning agents in one step), connects to MCP over stdio and SSE, runs on any modern LLM (OpenAI, DeepSeek, Qwen, and more), and outputs OpenAI‑compatible streaming APIs for instant drop‑in with any chat interface. Small, modular, and skill‑ready — spin it up in five minutes.

News

• [2026-05-29] LightAgent v0.7.0 Development: Adds opt-in trace observability with structured run/model/tool/error events, agent.export_trace(), and prompt-safe model request summaries for production debugging.
• [2026-05-28] LightAgent v0.6.5 Released: Adds opt-in structured run results, structured streaming events, catchable LightAgent errors, and tool argument validation while keeping legacy agent.run() and stream=True behavior compatible.
• [2026-05-27] LightAgent v0.6.4 Released: Improves runtime tool dispatch reliability, adds structured error codes and troubleshooting guidance, expands OpenAI-compatible provider documentation for OpenRouter and local models, and updates browser-use integration examples.
• [2026-04-26] LightAgent v0.6.0 Released: Completely refactors the core system architecture and introduces native skill support, enabling more modular, extensible, and task-oriented agent capabilities.
• [2026-02-21] LightAgent v0.5.0 Released: Adds session-level toolset constraints for granular control, fixes tool call history in multi-turn conversations, and improves LightSwarm stability.
• [2026-01-20] LightAgent v0.4.8 Released: Introduces runtime toolset constraints for session-level control and enhanced debug settings.
• [2025-11-15] LightAgent v0.4.7 Released: Improved debug configuration and fixes for LightSwarm-related bugs.
• [2025-10-28] LightAgent v0.4.6 Released: Adds support for model extension parameters (e.g., Qwen3 thinking mode) and enhanced metadata handling.
• [2025-09-16] Our paper is now available as a preprint on arXiv: https://arxiv.org/pdf/2509.09292. We invite the research community to read and cite our work.
• [2025-06-12] We are pleased to announce the official release of LightAgent v0.4.0! This version upgrade brings architectural improvements, with significant enhancements in performance, stability, and maintainability.
• [2025-05-05] LightAgent v0.3.3 Released: Deep Langfuse Logging Integration, Enhanced Context Management and Tool Invocation Stability View
• [2025-04-21] LightAgent v0.3.2 adds an adaptive Tools mechanism, supports unlimited intelligent tool filtering, reduces Token consumption by 80%, and improves response speed by 52%! View
• [2025-04-01] LightAgent v0.3.0 Support browser interaction browser_use and fully supports the MCP protocol, enabling collaborative work with multiple models and tools to achieve more efficient handling of complex tasks.View MCP release introduction.>>
• [2025-02-19] LightAgent v0.2.7 supports deepseek-r1 model for tot now.Significantly enhances the multi-tool planning capability for complex tasks.
• [2025-02-06] LightAgent version 0.2.5 is released now.
• [2025-01-20] LightAgent version 0.2.0 is released now.
• [2025-01-05] LightAgent version 0.1.0 is released now.

✨ Features

• Lightweight and Efficient 🚀: Minimalist design, quick deployment, suitable for various application scenarios. (No LangChain, No LlamaIndex) The core framework stays small, modular, and fully open source while using focused dependencies for provider, MCP, memory, and tracing integrations.
• Memory Support 🧠: Supports custom long-term memory for each user, natively supporting the mem0 memory module, automatically managing user personalized memory during conversations, making agents smarter.
• Autonomous Learning 📚️: Each agent possesses autonomous learning capabilities, and admins with permissions can manage each agent.
• Tool Integration 🛠️: Support for custom tools (Tools) and MCP tool integration, flexible expansion to meet diverse needs.
• Complex Goals 🌳: Built-in Tree of Thought (ToT) module with reflection, supporting complex task decomposition and multi-step reasoning, enhancing task processing capabilities.
• Multi-Agent Collaboration 🤖: Simpler to implement multi-agent collaboration than Swarm, with built-in LightSwarm for intent recognition and task delegation, enabling smarter handling of user input and delegating tasks to other agents as needed.
• Independent Execution 🤖: Tasks and tool calls are completed autonomously without human intervention.
• Multi-Model Support 🔄: Compatible with OpenAI-style providers such as OpenAI, OpenRouter, Zhipu ChatGLM, Baichuan, StepFun, DeepSeek, Qwen, vLLM, llama.cpp, and other OpenAI-compatible endpoints.
• Streaming API 🌊: Supports OpenAI streaming format API service output, seamlessly integrates with mainstream chat frameworks, enhancing user experience.
• Trace Observability 🔎: Opt-in trace=True run traces record structured run lifecycle, model request summaries, tool calls, tool results, and errors without changing the default string return value.
• Tool Generator 🚀: Just provide your API documentation to the [Tool Generator], which will automatically create exclusive tools for you, allowing you to quickly build hundreds of personalized custom tools in just 1 hour to improve efficiency and unleash your creative potential.
• Agent Self-Learning 🧠️: Each agent has its own scene memory capabilities and the ability to self-learn from user conversations.
• Adaptive Tool Mechanism 🛠️: Supports adding an unlimited number of tools, allowing the large model to first select a candidate tool set from thousands of tools, filtering irrelevant tools before submitting context to the large model, significantly reducing token consumption.

🧩 Multi-agent troubleshooting (failure map)

If you are using LightSwarm or other multi-agent patterns and start seeing role drift, cross-agent memory issues or confusing logs, you can check the Multi-agent failure map for a small symptom → mode → debug checklist.
This page is docs-only and does not change any framework code.

📋 FAQ

For common installation, model provider, tool, memory, MCP, Skills, streaming, and LightSwarm questions, see FAQ.

For shared long-term memory or graph memory deployments, review the Memory Security Guidance.

For OpenRouter, local LLM, and OpenAI-compatible provider setup, see Model Provider Configuration.

For structured error codes and troubleshooting hints, see Error Handling.

For v0.7.0 trace observability, see Trace Observability.

For browser-use integration with recent browser-use versions, see browser-use Integration.

🚧 Coming Soon

• Agent Collaborative Communication 🛠️: Agents can also share information and transmit messages, achieving complex information communication and task collaboration.
• Agent Assessment 📊: Buil