Our take
Activeregular commits and releases- Activity
- 91
- Community
- 28
- Issues
- 90
- Pull requests
- 79
- Releases more often than 93% of the projects we track
- Merges more pull requests than 86% of the projects we track
- Closes issues faster than 82% of the projects we track
LibrAgent is an actively maintained, feature-rich desktop agent environment, though its development is heavily concentrated in one contributor.
Good fit if
- You want a desktop interface for MCP tools and agent coordination rather than building a harness from code.
- You need to choose between cloud providers and Ollama while working with local files.
- You are comfortable adopting a rapidly developed MIT-licensed project with ongoing releases.
Look elsewhere if
- Your workflow requires a fully tested project: the supplied project facts indicate no test suite.
- You need a project with development responsibility spread across multiple contributors.
- You need an agent framework or library to embed in your own application rather than a desktop product.
All health signals
| Last commit | 2026-10-12 (3 days ago) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 100+ (latest v0.9.25, 2026-10-12) |
| Contributors | 6 (top contributor: 87% of commits) |
| Issues closed, last 90 days | 24+ (typically closed in 0 days) |
| Pull requests merged, last 90 days | 77 (typically merged in 0 days) |
| Project age | 15 months |
Checked on 2026-10-15 with the GitHub API.
Overview
LibrAgent is a Tauri desktop application for operating AI agents without assembling a framework or editing MCP configuration files by hand. It brings model selection, one-click tool installation, local workspaces, and agent coordination into one interface, with completed work saved as files on your machine.
It is aimed at people who want agent workflows without vendor-specific harnesses or manual setup. The application runs on Windows, macOS, and Linux, and supports cloud model providers as well as local Ollama models.
Key Features
- Connect to supported cloud models or select a local model through Ollama.
- Install MCP tool presets with one click, or import configurations from Cursor, VS Code, Claude Code, and Windsurf.
- Use bundled coordination skills for sequential pipelines, hub-and-spoke delegation, parallel task splitting, and multi-perspective review.
- Work against a local directory with workspace tools for reading and editing files.
- Use built-in shell, browser, knowledge, planning, and scheduled-task capabilities.
- Create recipes and scheduled tasks, including the documented Morning Briefing workflow.
- Apply session safeguards such as file path and command guards, context compaction, and loop prevention.
Use Cases
- A developer can install a GitHub MCP preset, attach a repository, and ask for a review report saved in the workspace.
- An operator can configure a scheduled briefing recipe and review its generated report in the application.
- A researcher can use pipeline or divide-and-conquer skills to produce a consolidated report from staged or independent tasks.
- A privacy-sensitive user can run an Ollama model and keep workspace interactions on their local machine.
What you need
Detected in the repository
- Node.js >=20 (from package.json)
- Automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Download an installer for Windows, macOS, or Linux from the latest releases. For development, the README gives this setup:
git clone https://github.com/fritzprix/libr-agent
cd libr-agent
pnpm install
pnpm tauri dev
See the README and user guide for model setup, extensions, and workflows.
Alternatives
- Orkas: Orkas coordinates a Commander and specialist agents from one chat, while LibrAgent centers on local workspaces, MCP tools, and configurable model providers.
- deepchat: DeepChat combines model chat with MCP tools, Skills, ACP agents, and messaging controls; LibrAgent focuses on workspace-based agent coordination.
- orca: Orca focuses on coding agents in isolated Git worktrees across local and remote environments, while LibrAgent offers a broader desktop agent workspace.
- agent-orchestrator: Agent Orchestrator centers on Git-backed coding tasks, worktrees, and pull request workflows; LibrAgent provides a general-purpose desktop environment for agents.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| LibrAgent | Rust | MIT | 11 | Active |
| Orkas | JavaScript | MIT | 2.1k | New |
| deepchat | TypeScript | Apache-2.0 | 6.4k | Active |
| orca | TypeScript | MIT | 88.6k | Active |
| agent-orchestrator | Go | Apache-2.0 | 12.7k | Active |
Considerations
The project is young, and although commits and releases are regular, most contributions come from one person, which may affect continuity and review capacity. The project facts also report no test suite, so teams should validate important workflows before relying on them. Development requires Node.js 20 or later; the README's developer setup also uses pnpm and Tauri. The MIT license permits broad use, while cloud models and remote MCP connections can involve external services when enabled.
Found this useful?
Share it with someone who would like LibrAgent.