Trampoline-AI / predict-rlm
Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Multimodal. process images and rendered document pages through sub-LM
- Async tool calling. native RLM async support in the WASM sandbox,
- Skills & tools. bundle domain instructions, PyPI packages, sandbox
- Simple file I/O. pass local files and mutable workspaces as typed inputs,
- Structured sub-LM calls. native Pydantic and DSPy signature support for
Get started
uv add predict-rlm- Maintenance
- Active
- Last commit 13 days ago
- Stars
- 437
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.13.2
- Released 13 days ago
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 50% closed
- 9 still open
- Pull requests
- 45 merged
- 3 waiting
- Releases
- 32
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ax-llm / ax | 2,978 | 6 days ago | Apache-2.0 | No downloads |
| originalankur / GenerateAgents.md | 261 | 8 months ago | MIT | No downloads |
| deepfates / imp | 260 | 17 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 97%
- JavaScript 3%
- Shell <1%
- Makefile <1%
Topics
- dspy
- llm
- rlm
Project record
- JobOther AI tools
- StatusListed
- Commits394
- Forks47
- Watching5
- Stars in 28 days+2
- CreatedMar 26, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026