Xia Zhenhua 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
..
_instructions bf14b47890 feat: make other agents support asking user input in MessageAction. (#1777) hai 1 ano
coder 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
commit_writer 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
manager 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
math_agent 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
postgres_agent 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
repo_explorer 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
study_repo_for_task 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
typo_fixer_agent 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
verifier 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
README.md c7dd443fa2 CoderAgent: Render summary prompt conditionally (#1461) hai 1 ano
agent.py 76abca361c feat: simplify state.history with to_memory call in micro-agent. Or the call to LLM may exceed the token limit. (#1806) hai 1 ano
instructions.py f8d4b1ab0d Use generic types (#1680) hai 1 ano
registry.py 0c2ebfd6e1 Ruff: use I rule for isort (#1410) hai 1 ano

README.md

Introduction

This package contains definitions of micro-agents. A micro-agent is defined in the following structure:

[AgentName]
├── agent.yaml
└── prompt.md

Note that prompt.md could use jinja2 template syntax. During runtime, prompt.md is loaded and rendered, and used together with agent.yaml to initialize a micro-agent.