Idea: long-term memory for the agent across restarts

#1
by Corbenic - opened

Your ToolCallingAgent example is already wired for a local Ollama model (qwen2.5:7b at 127.0.0.1:11434), with a DuckDuckGo search tool and up to 20 steps. That is a good self-hosted path, but if Ollama or the Space restart, the agent must recompute the prompt templates and the tool schemas. Galahad is a long-term memory for the agent: it save and restore the KV cache byte-for-byte across restarts, so the agent skip recomputation and keep memory between sessions. In our tests, restore 2.8 to 4.3x faster than recompute, and it can keep 50M tokens on disk. Would you be open to try it with Ollama, or want help integrating? https://github.com/corbenicai/galahad

Sietse

Sign up or log in to comment