bob_llm
- Software
- Middleware
- Tool
A ROS 2 node that runs as an autonomous AI agent, talking to any OpenAI-compatible LLM endpoint while managing chat history, tool calls and runtime-loaded skills.
Source on GitHub: github.com/bob-ros2/bob_llm (opens in a new tab). Facts read at commit b50b3f7 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit b50b3f7 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Connects to any OpenAI-compatible LLM backend such as Ollama, vLLM, llama-cpp-python or commercial APIs.
- Keeps conversational state and feeds the chat history back to the model as context.
- Loads Python functions from user modules and exposes them to the model as callable tools.
- Discovers, reads and runs self-contained skills following the Anthropic Agent Skills standard, with core and writable skill directories.
- Streams response tokens directly and publishes model reasoning on its own topic.
- Accepts multimodal JSON prompts with images and ships an interactive terminal chat client with Markdown rendering.
Written by Robotheca from the project's README (opens in a new tab) at commit b50b3f7.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 10 Jun 2026 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.