Claude Recall vs. Simon Willison's llm
Simon Willison's llm CLI is the canonical local-LLM logger. SQLite-backed, plugin-friendly, decade of build-in-public. Claude Recall does the same idea but only for Claude Code sessions, with a Claude-Code-shaped UI on top.
TL;DR
- Use
llmif you talk to many LLMs and want one searchable log. - Use Claude Recall if Claude Code is your primary tool and you want first-class session-level features.
- Use both if you want a generic LLM log AND a Claude-Code-native search UI.
Side-by-side
| Capability | llm CLI | Claude Recall |
|---|---|---|
| SQLite-backed history | Yes | Yes |
| Multi-provider | Yes | Claude Code only |
| Plugin ecosystem | Yes | Not yet |
| Long-form record of every prompt | Yes | Yes |
| Claude Code session as a first-class object | No | Yes |
| Pipe a past session into a new conversation | Manual | recall context <id> | claude |
| Web UI / browser timeline | No | Yes |
| Project / tag organization | Light | Yes |
| MCP server | No | Yes |
| Cost analytics per Claude session | No | Yes |
| Five-plus years of community trust | Yes (11.7K stars) | Small, growing |
Where they win
llmis the right tool if you talk to many models. It captures every prompt across providers into one SQLite database with a clean plugin interface. The community around it (Simon, the Datasette ecosystem) is exceptional. If your use is broad and your favorite model is “whichever one is cheapest today,” llm is the answer.
Where we win
Claude Recall is purpose-built for the Claude Code session as a unit of work. A session has structure (tool calls, file edits, sub-tasks), not just a prompt-response pair. Claude Recall indexes that structure, makes it searchable, and pipes any historical session back into a new Claude Code conversation as condensed context. That is a workflow llm was not built for. The MCP server, cost analytics, and project-aware UI are all consequences of choosing the narrower scope.
When to pick which
- Use
llmfor general-purpose multi-model logging. - Use Claude Recall when Claude Code is your main interface and you want session-shaped memory.
Coexistence
They do not conflict; you can run both. llm will continue to log your llm invocations; Claude Recallwill continue to index your Claude Code sessions. The two databases live in different places.
FAQ
Is this llm for Claude Code?
That is the closest one-line analogy and it is how the project is positioned. The implementation is independent.
Will Claude Recall add multi-provider support?
Not in 2026. Scope discipline is the moat.
Should I install both?
If you are already an llm user, yes. They are complementary.