# agentica

> Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。

- **URL**: https://www.freshcrate.ai/projects/agentica
- **Author**: shibing624
- **Category**: MCP Servers
- **Latest version**: `v1.4.6` (2026-06-03)
- **License**: Apache-2.0
- **Source**: https://github.com/shibing624/agentica
- **Homepage**: https://shibing624.github.io/agentica/
- **Language**: Python
- **GitHub**: 279 stars, 37 forks
- **Registry**: github
- **Tags**: `actionflow`, `agent`, `agentica`, `agents`, `langchain`, `llm`, `multi-agent`, `python`, `workflows`

## Description

Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.4.6` | 2026-06-03 | High | Cross-provider fallback now supports tool-calling turns: the fallback model can run tools and answer, while its provider-specific transcript is compacted (identity-marker based) so replay to the recovered primary stays clean. Fallback models are cloned per run for concurrency safety, and candidate dedup uses object identity. Adds edit-time LSP diagnostics CLI flags (--enable-diagnostics/--diagnostics-server), richer agentica doctor (workspace git + multi-server LSP checks, graceful MCP degradati |
| `v1.4.4` | 2026-05-11 | High | ## Highlights  ### perf(hooks): MemoryExtractHooks 优化  - 新增 `WorkspaceMemoryConfig.auto_extract_memory_background: bool = False` —— 开启后 memory 抽取以 `asyncio.create_task` 后台运行，**不再阻塞 `on_agent_end`**。适用于 FastAPI / asyncio.run 等长 event loop 场景，砍掉每轮响应 ~30s 抽取延迟。 - `MemoryExtractHooks` 现优先使用 `agent.auxiliary_model` 跑抽取调用，失败回退到 `agent.model`。副 model 通常更便宜更快，token 成本与主流程隔离。 - ⚠️ `auto_extract_memory_background=True` **不要**在 `agent.run_sync()` / `run_stream_sync()` 下使用：临时 loop 会在 task 完成前关闭，memory 静默丢失。 |
| `v1.4.3` | 2026-05-10 | High | Skill lifecycle refactor + VaG decoupling.  ## Breaking changes (PyPI users action required)  The skill lifecycle has been slimmed down. VaG (Verifier-as-Gatekeeper) experimental code is now a research module under `evaluation/vag/` and is no longer part of the SDK.  ### Removed public exports - `SkillCandidate`, `GateVerdict`, `SkillGateResult`, `SkillAdmissionGate`, `skill_fingerprint` - `PROVENANCE_FILENAME`, `get_provenance_path`, `append_provenance_event`, `read_provenance_events`  ### Remo |
| `v1.4.1` | 2026-04-28 | High | # v1.4.1 — DX overhaul: top-level exports, sync-first docs, history filter  ## Highlights  ### Simpler imports — no more deep paths `OpenAIChat` and the 6 default `Builtin*Tool`s are now eager top-level exports:  ```python from agentica import (     Agent, DeepAgent, Workspace, tool,     OpenAIChat,     BuiltinFileTool, BuiltinExecuteTool, BuiltinFetchUrlTool,     BuiltinWebSearchTool, BuiltinTodoTool, BuiltinTaskTool,     HistoryConfig, WorkspaceMemoryConfig, RunConfig, ) ```  Other model provi |
| `v1.4.0` | 2026-04-23 | High | ## What's Changed * [Draft] sdk-dev v1.3.6: packaging refactor + extras + API convergence by @shibing624 in https://github.com/shibing624/agentica/pull/25   **Full Changelog**: https://github.com/shibing624/agentica/compare/v1.3.4...v1.4.0 |
| `1.2.3` | 2025-12-21 | Low | ## What's Changed * Dev by @shibing624 in https://github.com/shibing624/agentica/pull/21   **Full Changelog**: https://github.com/shibing624/agentica/compare/1.1.0...1.2.3 |
| `1.0.10` | 2025-06-19 | Low | # v1.0.10  修复后的效果： ✅ 推理内容完整且无重复 ✅ 流式和非流式响应的推理内容一致 ✅ 正确处理大量小 chunk 的累积（如 deepseek-r1 的reasoning chunks） ✅ 支持各种推理模型（o1、deepseek-r1、gemini-2.5-pro 等）  **Full Changelog**: https://github.com/shibing624/agentica/compare/1.0.7...1.0.10 |
| `1.0.6` | 2025-05-19 | Low | # v1.0.6  ## Support Model Context Protocol (MCP) Tools  This module provides a client implementation for the [Model Context Protocol (MCP)](https://spec.modelcontextprotocol.io/), allowing you to easily integrate MCP servers with your Agentica agents.  ## Features  - Support for stdio, SSE, and StreamableHttp transport modes - Explicit parameter names for each transport type - Async context manager-based API for easy resource management - Tool caching for improved performance - Auto |
| `1.0.0` | 2025-04-20 | Low | ## v1.0.0  # Model Context Protocol (MCP) Tools  This module provides a client implementation for the [Model Context Protocol (MCP)](https://spec.modelcontextprotocol.io/), allowing you to easily integrate MCP servers with your Agentica agents.  ## Features  - Support for both stdio and SSE transport modes - Explicit parameter names for each transport type - Async context manager-based API for easy resource management - Tool caching for improved performance - Automatic tool registrat |
| `0.2.3` | 2024-12-29 | Low | ## v0.2.3  ZhipuAI提供了免费的模型api，包括：模型：glm-4-flash, glm-4v-flash, CogView-3-Flash, CogVideoX-Flash 和工具：文档（PDF、DOC、PPT、JPG等格式）内容抽取,  Web-Search-Pro  免费专区：https://bigmodel.cn/dev/activities/free/glm-4-flash  均已经兼容到agentica库。  调用示例：  https://github.com/shibing624/agentica/blob/main/examples/40_web_search_zhipuai_demo.py      **Full Changelog**: https://github.com/shibing624/agentica/compare/0.2.0...0.2.3 |

## Citation

- HTML: https://www.freshcrate.ai/projects/agentica
- Markdown: https://www.freshcrate.ai/projects/agentica.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/agentica/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._