🚀 I just open-sourced chatstore — a lightweight, framework-agnostic persistent chat library for LLM applications.
If you've ever built an AI assistant or agent, you know the pain: → Where do I store conversation history?
→ How do I feed a sliding window to the LLM without blowing the context limit?
→ How do I retrieve relevant past context without spinning up a server?
Most solutions either lock you into a framework (LangChain), require Docker + a running server (Zep), or need an LLM call just to store a memory (Mem0).
chatstore does none of that.
✅ One class. Zero infrastructure.
✅ Works with any LLM — OpenAI, Gemini, Anthropic, Ollama, anything
✅ Persistent history backed by SQLite (swappable to Postgres)
✅ Sliding window context — configurable, token-aware
✅ Optional semantic search with local embeddings (no API key needed)
𝗩𝗲𝗿𝘀𝗶𝗼𝗻 𝟭 — drop in and go:
pip install chatstore
𝗩𝗲𝗿𝘀𝗶𝗼𝗻 𝟮 — add vector memory with one flag:
pip install chatstore[semantic] Start using it in 3 lines:
from chatstore import ChatService
chat = ChatService(project_id="my_app")
chat.save_message("user", "Hello!")
That's it. No config files. No environment setup. No servers.
🔗 GitHub → [https://github.com/namankr/chatstore](https://github.com/namankr/chatstore)
If this saves you even an hour of boilerplate work, drop a ⭐ on the repo — it genuinely helps more developers discover it.
And if you're building something with LLMs, I'd love to hear what you're working on. Drop a comment or DM me 👇