adobe-research / dynasaur
Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"
Why this job: works in the areas we cover, but does not say which job it does
What it does
DynaSaur is a dynamic LLM-based agent framework published at COLM 2025 that uses a programming language as a universal representation of its actions. At each step, it generates a Python snippet that either calls on existing actions or creates new ones when the current action set is insufficient. These new actions can be developed from scratch or formed by composing existing actions, gradually expanding a reusable library for future tasks.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 362
- On GitHub
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 33% closed
- 2 still open
- Pull requests
- 0 merged
- 3 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| jncraton / languagemodels | 1,187 | 8 months ago | MIT | No downloads |
| screenpipe / screenpipe | 22,354 | yesterday | Custom | No downloads |
| bilibili / Index-1.9B | 1,038 | 17 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- agents
- agi
- llm
- ai
- nlp
Project record
- JobOther AI tools
- StatusListed
- Commits8
- Forks32
- Watching30
- Stars in 28 days0
- CreatedOct 23, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026
