deer-flow / llm-space
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Build. write and version your prompts, system messages, tools, and model settings.
- Trace. see every model call and tool run inside the agent loop as it happens.
- Debug. replay a run from history and step through it to find what went wrong.
- Evaluate. measure how your agent performs across runs.
- Manage. keep your threads organized as files on your own machine.
Get started
bun install- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 2,121
- +24 this week
- Licence
- MIT
- Allows business use
- Downloads for
- 2 systems
- Mac, Linux
- Latest version
- v4.20.0
- Released 31 days ago
- Built with
- TypeScript
- 97% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 83% closed
- 6 still open
- Pull requests
- 115 merged
- 20 waiting
- Releases
- 46
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| cubeplexai / cubeplex | 575 | 2 days ago | Custom | No downloads |
More: download files, languages, topics and project record
Download files, v4.20.0
- Mac4 files, 665 downloads
- Linux4 files, 203 downloads
Languages
- TypeScript 97%
- Python 2%
- JavaScript 1%
- CSS <1%
Topics
- agent
- deer-flow
- develop
- electrobun
- harness
- llm
- llm-tools
- managed-agents
Project record
- JobOther AI tools
- StatusListed
- Commits788
- Forks230
- Watching6
- Stars in 28 days+98
- CreatedJun 28, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026