[PR #130] [CLOSED] add LeAgent integration guide

bsakaguchi commented

2026-10-26 09:46:55 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/130
Author: @vixues
Created: 5/22/2026
Status: ❌ Closed

Base: main ← Head: main

📝 Commits (2)

8a837c9 add LeAgent integration guide
a621e12 fit contributing guide

📊 Changes

4 files changed (+106 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/leagent.md (+52 -0)
➕ docs/leagent.zh-CN.md (+52 -0)

📄 Description

LeAgent is an open-source desktop AI agent that combines multi-turn chat, a visual workflow builder, 100+ built-in tools, a declarative rule engine, Agent Skills, and MCP — all in a single self-hostable stack.

Agent runtime — multi-turn sessions with streaming, tool execution, tiered model routing, layered prompts, and episodic / semantic / procedural cognitive memory
Skills — Agent Skills v1.0 SKILL.md bundles with progressive disclosure and on-demand loading; built-in skills, install from links/archives, and a pluggable HTTP skill registry
100+ offline tools — documents, web, data, code execution, databases, generative UI, coding projects, and more
Sidebar desk pet — customizable avatar and background, walk/jump animations, and personality bubbles; upload PNG / SVG / GIF or sprite sheets, synced with chat streaming and session state
Visual workflows — ReactFlow editor with YAML export, templates, and every tool as a typed node
Multi-provider LLM — DeepSeek, DashScope (Qwen), OpenAI, Ollama, vLLM, and more (DeepSeek is currently the most thoroughly validated; recommended for first use)
Zero-config default — SQLite out of the box, single Docker container, optional PostgreSQL / Milvus

Checklist

Agent Configuration

Model names are current (v4-pro / v4-flash, not v3 names)
1M context is configured or mentioned
Max thinking effort level is supported
Pricing is current (input, output, cache hit) — N/A, not included
Config fields are verified to work in the agent
No workarounds for already-fixed upstream bugs

Documentation

Both English and Chinese versions included in a single PR
README table entry inserted in alphabetical order
One tool per PR; unrelated tools not combined
Images placed in docs/assets/ with descriptive filenames and reasonable sizes — N/A, no images

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/130 **Author:** [@vixues](https://github.com/vixues) **Created:** 5/22/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (2) - [`8a837c9`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/8a837c9675d0e6ff9669b9261950c975c41d1d69) add LeAgent integration guide - [`a621e12`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/a621e12d3f58e08571f94ca55e8559026212adf6) fit contributing guide ### 📊 Changes **4 files changed** (+106 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/leagent.md` (+52 -0) ➕ `docs/leagent.zh-CN.md` (+52 -0) </details> ### 📄 Description [**LeAgent**](https://github.com/vixues/LeAgent) is an open-source desktop AI agent that combines multi-turn chat, a visual workflow builder, 100+ built-in tools, a declarative rule engine, Agent Skills, and MCP — all in a single self-hostable stack. - **Agent runtime** — multi-turn sessions with streaming, tool execution, tiered model routing, layered prompts, and episodic / semantic / procedural cognitive memory - **Skills** — [Agent Skills v1.0](https://agentskills.my/specification) `SKILL.md` bundles with progressive disclosure and on-demand loading; built-in skills, install from links/archives, and a pluggable HTTP skill registry - **100+ offline tools** — documents, web, data, code execution, databases, generative UI, coding projects, and more - **Sidebar desk pet** — customizable avatar and background, walk/jump animations, and personality bubbles; upload PNG / SVG / GIF or sprite sheets, synced with chat streaming and session state - **Visual workflows** — ReactFlow editor with YAML export, templates, and every tool as a typed node - **Multi-provider LLM** — DeepSeek, DashScope (Qwen), OpenAI, Ollama, vLLM, and more (DeepSeek is currently the most thoroughly validated; recommended for first use) - **Zero-config default** — SQLite out of the box, single Docker container, optional PostgreSQL / Milvus ![screen shot](https://i.imgur.com/rcNFnFd.png) --- ## Checklist ### Agent Configuration - [x] Model names are current (v4-pro / v4-flash, not v3 names) - [x] 1M context is configured or mentioned - [x] Max thinking effort level is supported - [x] Pricing is current (input, output, cache hit) — N/A, not included - [x] Config fields are verified to work in the agent - [x] No workarounds for already-fixed upstream bugs ### Documentation - [x] Both English and Chinese versions included in a single PR - [x] README table entry inserted in alphabetical order - [x] One tool per PR; unrelated tools not combined - [x] Images placed in `docs/assets/` with descriptive filenames and reasonable sizes — N/A, no images --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 09:46:55 +00:00