Source: https://seerepo.com/compare/BerriAI/litellm/vs/TabbyML/tabby
Markdown source: https://seerepo.com/compare/BerriAI/litellm/vs/TabbyML/tabby.md
Description: litellm and tabby share 26 technologies: axum, tower, sqlx, SQLite, OpenAI, Tokio, React, Next.js, jsonwebtoken, tracing, tracing-subscriber, Tailwind CSS, class-variance-authority, next-themes, React Hook Form, react-syntax-highlighter, recharts, cmdk, sonner, react-resizable-panels, Lucide, jwt-decode, react-markdown, remark-gfm, Zod, and @hookform/resolvers. litellm is written in Python and tabby in Rust.

# litellm vs tabby

litellm and tabby share 26 technologies: axum, tower, sqlx, SQLite, OpenAI, Tokio, React, Next.js, jsonwebtoken, tracing, tracing-subscriber, Tailwind CSS, class-variance-authority, next-themes, React Hook Form, react-syntax-highlighter, recharts, cmdk, sonner, react-resizable-panels, Lucide, jwt-decode, react-markdown, remark-gfm, Zod, and @hookform/resolvers. litellm is written in Python and tabby in Rust.

- [BerriAI/litellm](https://seerepo.com/r/BerriAI/litellm): The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
- [TabbyML/tabby](https://seerepo.com/r/TabbyML/tabby): Self-hosted AI coding assistant

## What they share and what sets them apart

- In common: axum, tower, sqlx, SQLite, OpenAI, Tokio, React, Next.js, jsonwebtoken, tracing, tracing-subscriber, Tailwind CSS, class-variance-authority, next-themes, React Hook Form, react-syntax-highlighter, recharts, cmdk, sonner, react-resizable-panels, Lucide, jwt-decode, react-markdown, remark-gfm, Zod, @hookform/resolvers
- Only in litellm: FastAPI, Flask, aws-sdk-s3, psycopg, rusqlite, sqlx-postgres, Postgres, moka, Redis, azure_storage_blob, Claude, Qdrant, anyio, AIOHTTP, Anthropic, aws-sdk-sts, azure_identity, gcp_auth, litellm, rmcp, tokenizers, tiktoken, tiktoken-rs, jinja2, zip, Pydantic, schemars, jsonschema, boto3, azure_core, aws-sdk-secretsmanager, tanstack, Base UI, react-copy-to-clipboard, react-hotkeys-hook, usehooks-ts, @shadcn/react, ProseMirror, prosemirror-state, prosemirror-view, react-json-view-lite, @heroicons/react, papaparse
- Only in tabby: sqlx-sqlite, cached, GitHub, Streamlit, axum-extra, lru-cache, PostHog, indicatif, spinners, utoipa-swagger-ui, argon2, openidconnect, text-splitter, ollama-rs, jsonlines, htmd, lettre, validator, OpenTelemetry, opentelemetry_sdk, opentelemetry-otlp, tracing-opentelemetry, @orama/orama, toml, pino, react-email, @codemirror/theme-one-dark, tailwind-merge, Radix UI, CodeMirror, tiptap, Framer, react-day-picker, @uidotdev/usehooks, react-textarea-autosize, react-intersection-observer, downshift, react-activity-calendar, react-json-view, tippy.js, @uiw/codemirror-extensions-langs, cm6-graphql, embla-carousel-autoplay, embla-carousel-react, react-error-boundary, react-lazy-load, react-topbar-progress-indicator, @radix-ui/react-icons, @urql/exchange-auth, dompurify, he, marked, mdast, remark-math, rehype-raw, rehype-sanitize, remark-stringify, unified, hast, remark, unist-util-visit

## Side by side

| | litellm | tabby |
|---|---|---|
| Size | 4,586,231 lines written, 5,606 code files | 146,843 lines written, 1,069 code files |
| Who writes it | 20.1% of its commits signed by AI. With Claude Code, Devin, Cursor, GitHub Copilot, OpenHands, Codex, Aider, and Gemini CLI | 0.2% of its commits signed by AI. With GitHub Copilot and CodeRabbit |
| Activity | Last push November 5, 2026, 46,240 commits, 62,741 stars | Last push June 30, 2026, 3,670 commits, 33,923 stars |
| Tests | 6,918 test files. 22% of its code files have a test that imports them | 35 test files. 5.6% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, litellm or tabby?

litellm, with 4,586,231 lines written; tabby has 146,843.

The proof: [BerriAI/litellm's code at commit 7e4ad6e](https://github.com/BerriAI/litellm/tree/7e4ad6eb333071d67c2eb03ce6468f89a0855027)

### Which has more GitHub stars, litellm or tabby?

litellm, with 62,741 stars; tabby has 33,923.

The proof: [BerriAI/litellm on GitHub](https://github.com/BerriAI/litellm)

### Which has more tests, litellm or tabby?

litellm, with 6,918 test files; tabby has 35.

The proof: [BerriAI/litellm's code at commit 7e4ad6e](https://github.com/BerriAI/litellm/tree/7e4ad6eb333071d67c2eb03ce6468f89a0855027)

### Which was updated more recently, litellm or tabby?

litellm: its last push was on November 5, 2026, and tabby's on June 30, 2026.

The proof: [BerriAI/litellm's commits on GitHub](https://github.com/BerriAI/litellm/commits)

### Which has more commits signed by AI, litellm or tabby?

litellm: an AI signed 20.1% of its commits, with Claude Code, Devin, Cursor, GitHub Copilot, OpenHands, Codex, Aider, and Gemini CLI; in tabby, 0.2%.

The proof: [the commits each tool signed in BerriAI/litellm](https://seerepo.com/r/BerriAI/litellm/ai)

## Sources

- BerriAI/litellm: Read on November 5, 2026, at commit 7e4ad6e (https://github.com/BerriAI/litellm/tree/7e4ad6eb333071d67c2eb03ce6468f89a0855027)
- TabbyML/tabby: Read on November 7, 2026, at commit 21b2904 (https://github.com/TabbyML/tabby/tree/21b29048d7bcf6b94f9f482f2d0fd05efadfd19f)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.