AIToday
Large Language ModelsOpen-Source AIHacker NewsPublished: Aug 17, 2026, 01:00 JST2 min read

Sib: Git-based LLM client replaces SQLite with version control

Sib: Git-based LLM client replaces SQLite with version control

Key takeaway

  • Sib is a command-line LLM client that stores conversations as Git commits instead of a database, giving users version control, branching, and backup for free through Git's native features.

  • Each user prompt and assistant response becomes a separate commit, allowing users to fork conversations, edit past turns, and share chains via any Git host—collapsing features like Repeat, Edit, and Fork into a single Git-based system.

3 Key Points

  1. What happened

    A developer released Sib, a command-line LLM client that stores conversations as Git commits instead of using a traditional database like SQLite. Each user prompt and AI response becomes a commit in a Git repository.

  2. Why it matters

    By using Git as the storage backend, Sib gives users built-in version control (branching, editing, rewinding), automatic backup, and sharing capabilities without extra code—features that typically require separate implementations in other LLM clients. The approach treats conversations as code-like artifacts with full history and collaboration tools.

  3. What to watch

    The project is in early stages and the codebase is not yet stable for large feature work; the creator invites contributions to shape the core API. Installation requires bash ≥ 3.2, Git, jq, curl, awk, and coreutils, and works with any LLM endpoint (defaults to OpenAI).

Ask the AI about this article →

Context & Analysis

Sib reimagines LLM conversation storage by treating conversations as version-controlled artifacts rather than database records. Instead of building separate features for undo, branching, backup, and sharing—as most LLM clients do—Sib achieves all of them through Git's native capabilities. A conversation is a linear chain of commits, each containing a JSON object with role (user or assistant), content, and metadata. When you ask a prompt, Sib reads the entire chain from HEAD, sends it to the LLM endpoint, and records both the user turn and assistant response as two new commits. This design naturally supports forking (by choosing a parent commit other than HEAD), editing (by creating a new branch from an earlier point), and sharing (by pushing to any Git remote).

The creator built Sib around a deliberate philosophy: rather than shipping each capability as a named feature, let users control context the way Git does. The `-p` flag switches the parent commit, the `-r` flag skips stdin to move HEAD without an API call, and the `-n` flag starts a fresh chain—simple flags that compose into powerful workflows. Named saves (e.g., `sib save eva-3.0-go-off`) let users label important conversation points without memorizing commit hashes. The project is explicitly in early stages; the codebase is not yet stable for large feature work, but the creator invites involvement in shaping the core API.

FAQ

How do I install Sib?
Clone the repository from https://github.com/sib-project/sib, then run `make PREFIX="$HOME/.local" install` for a user-level install or `make install` for global install. You need bash ≥ 3.2, git, jq, curl, awk, and coreutils as dependencies.
Can I edit or restart a conversation?
Yes. Use `sib ask -p HEAD~1` to repeat the last prompt (like a Repeat button), or `sib ask -p HEAD~2` with a new prompt to fork from an earlier turn (like an Edit button). The `-p` flag lets you choose any commit as the parent for the next response.
How do I share conversations with others?
Push your local conversation to any public Git repository using `sib git push <your-repo-url> <local-ref>:refs/heads/<remote-ref>`, then others can fetch it with `sib git fetch`. You can also publish to the official sib-project/hub by pushing and opening a share issue.

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Nvidia revives Rubin CPX chip with major redesignYahoo Finance AI · 2h ago
  • AI advice followed by 79%, but well-being unchangedITmedia AI+ · 5h ago
  • Enterprises face agent governance gapSiliconANGLE AI · 8h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleObserve launches MCP server and CLI for AI agents to query telemetry data