Source: https://seerepo.com/compare/BerriAI/litellm/vs/vectorize-io/hindsight
Markdown source: https://seerepo.com/compare/BerriAI/litellm/vs/vectorize-io/hindsight.md
Description: litellm and hindsight share 6 technologies: Next.js, React, FastAPI, Postgres, OpenAI, and Claude. Both are written in Python.

# litellm vs hindsight

litellm and hindsight share 6 technologies: Next.js, React, FastAPI, Postgres, OpenAI, and Claude. Both are written in Python.

- [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]
- [vectorize-io/hindsight](https://seerepo.com/r/vectorize-io/hindsight): Hindsight: Agent Memory That Learns

## What they share and what sets them apart

- In common: Next.js, React, FastAPI, Postgres, OpenAI, Claude
- Only in litellm: Flask, axum, Redis, Anthropic
- Only in hindsight: None

## Side by side

| | litellm | hindsight |
|---|---|---|
| Size | 4,405,837 lines written, 5,630 code files | 744,037 lines written, 1,156 code files |
| Who writes it | 20% of its commits signed by AI. With Claude Code, Devin, Cursor, GitHub Copilot, OpenHands, Codex, Aider, and Gemini CLI | 6.9% of its commits signed by AI. With Claude Code, Cursor, Codex, and GitHub Copilot |
| Activity | Last push October 30, 2026, 45,956 commits, 62,405 stars | Last push October 30, 2026, 3,977 commits, 56,348 stars |
| Tests | 6,741 test files. 21.7% of its code files have a test that imports them | 1,319 test files. 30.2% 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 hindsight?

litellm, with 4,405,837 lines written in 5,630 code files; hindsight has 744,037 in 1,156.

The proof: [BerriAI/litellm's code at commit ef9385c](https://github.com/BerriAI/litellm/tree/ef9385c712297fa59bf8555962bfd719c55a4529)

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

litellm, with 62,405 stars; hindsight has 56,348.

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

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

litellm, with 6,741 test files; hindsight has 1,319.

The proof: [BerriAI/litellm's code at commit ef9385c](https://github.com/BerriAI/litellm/tree/ef9385c712297fa59bf8555962bfd719c55a4529)

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

Both got their last push on October 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 hindsight?

litellm: an AI signed 20% of its commits, with Claude Code, Devin, Cursor, GitHub Copilot, OpenHands, Codex, Aider, and Gemini CLI; in hindsight, 6.9%.

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

## Sources

- BerriAI/litellm: Read on October 30, 2026, at commit ef9385c (https://github.com/BerriAI/litellm/tree/ef9385c712297fa59bf8555962bfd719c55a4529)
- vectorize-io/hindsight: Read on October 30, 2026, at commit 8e8e9dc (https://github.com/vectorize-io/hindsight/tree/8e8e9dc9cde79c4053befae35d84119d6b3b7cde)

## 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.