by shizhl · Agent Tool · ★ 221
CoAgents The code for "cooperative and interactive agents framework" We propose the ConAgents, a Cooperative and interactive agents framework . The grounding agent generates tool-use instructions while execution agent executes selected tools. The observing agent extracts relevant values from execution results. When receiving feedback from the tool environment, the execution agent and observing agent adapt themselves iteratively. Quick start install the main library via register the TMDB platform to get the access token to access the TMDB APIs.
| Stars | 221 |
| Forks | 2 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 68.1881716902926/100 |
| Open Issues | 1 |
| Last Updated | 2024-03-26 |
| Created | 2024-02-13 |
| Platforms | python |
| Est. Tokens | ~31k |
Explore other popular agent tool tools:
CoAgents is Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents". It is categorized as a Agent Tool with 221 GitHub stars.
CoAgents is primarily written in Python. It covers topics such as agent, large-language-models, multi-agent.
You can find installation instructions and usage details in the CoAgents GitHub repository at github.com/shizhl/CoAgents. The project has 221 stars and 2 forks, indicating an active community.