howl-anderson / agentsilex
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
Why this job: says: agent framework; topics: agent-framework, ai-agent
What it does
- Single Agent Execution. Create and run individual agents with custom instructions
- Tool Calling. Agents can call external tools/functions to perform actions
- Tool Definition. Simple @tool decorator to define callable functions with automatic schema extraction
- Conversation Management. Session-based dialog history tracking across multiple turns
- Multi-Agent Handoff. Main agent can intelligently route requests to specialized sub-agents
Get started
pip install agentsilex- Maintenance
- Inactive
- Last commit 10 months ago
- Stars
- 460
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 82% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 2 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| langchain-ai / langchain | 149,378 | yesterday | MIT | No downloads |
| genlayerlabs / subzeroclaw | 140 | 53 days ago | MIT | No downloads |
| operand / agency | 491 | 8 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 82%
- JavaScript 12%
- HTML 6%
- Shell 1%
Topics
- agent-framework
- ai-agent
- anthropic
- educational
- gemini
- hackable
- litellm
- llm
- minimal
- openai
- pydantic
- python
Project record
- JobAgent frameworks
- StatusListed
- Commits35
- Forks47
- Watching21
- Stars in 28 days+3
- CreatedMay 1, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026