| ▲ | Axsuul 6 hours ago | |
Anyone else have related reading that touches on this? I'm building my own custom harness and want to start implementing loop support, etc. But I also want to build some sort of framework so that it's dynamic (e.g. this needs to run x number of iterations, while planning needs to run y number of iterations). | ||
| ▲ | zarldev 42 minutes ago | parent | next [-] | |
OpenAI and Anthropic both have blog posts about programmatic tool use. Tbh I settled in STARLARK as the intermediary language it's a python dialect so most llms can use it with little help.https://github.com/zarldev/zarlmono/blob/main/zkit%2Fagent%2... it's a wrapper around the calls of the other tool set. | ||
| ▲ | metadat 5 hours ago | parent | prev | next [-] | |
Check out https://github.com/strongdm/attractor along with the community implementations at https://factory.strongdm.ai/products/attractor#community. | ||
| ▲ | hagen8 6 hours ago | parent | prev | next [-] | |
Check out academic papers about: 1. Hierarchical skills, workflow, skill learning 2. Meta Harness, self-learning harnesses 3. Trace/trajectory representation 4. Common agentic benchmarks But first more basic things like 5. Blog posts form anthropic 6. How Claude Code/PI/ Hermes!! agent works 7. Agent sessions/ Forking/ Hooks | ||
| ▲ | alansaber 5 hours ago | parent | prev [-] | |
Sounds like you want something similar to /goal mode in Codex. | ||