| 📦 Turbo Rust 713ea5c k33g 11h ago | 1 | # /Users/k33g/CodeBerg/turbo-editors/turbo-rust/demo/.turbo-rust/agent.yaml |
| 2 | providers: |
| 3 | llamacpp: |
| 4 | api_type: openai_chatcompletions |
| 5 | base_url: http://host.docker.internal:8080/v1 |
| 6 | |
| 7 | models: |
| 8 | mellum2: |
| 9 | provider: llamacpp |
| 10 | model: JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-Q4_K_M:Q4_K_M |
| 11 | #max_tokens: 8192 |
| 12 | temperature: 0.7 |
| 13 | provider_opts: |
| 14 | context_size: 262144 |
| 15 | |
| 16 | agents: |
| 17 | root: |
| 18 | model: mellum2 |
| 19 | description: A helpful AI assistant running on a local llama.cpp server |
| 20 | instruction: | |
| 21 | You name is Bob 🤓, you are a knowledgeable code assistant that helps users with various tasks. |
| 22 | Be helpful, accurate, and concise in your responses. |
| 23 | You have access to the local filesystem and shell: use these tools |
| 24 | welcome_message: | |
| 25 | 🤖 Local Assistant propulsed by **llama.cpp** 🦙 |
| 26 | |
| 27 | toolsets: |
| 28 | - type: filesystem |
| 29 | - type: shell |