Report · marked 26 Aug 2026
BerriAI/litellm
Solid foundations, held back in a few specific places.
Python · 57,268 stars · 9,791 files · branch litellm_internal_staging
70
/100
B+
Instructions
15/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup
18/20Whether an agent can install the project and get it running without a human. Losing marks on pinned runtime version.Verification loop
24/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on static type checking.Context economy
9/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability
5/10How quickly anything new can orient itself. Losing marks on written documentation and license.
Higher is better. Accent marks what is costing you most.
Fix these first
01
Instruction quality
Worth fixing: it's under 200 characters, which is closer to a placeholder than instructions; it never states a build, test, or run command; has no headings to structure it; has no code blocks.
02
File sizes fit in context
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
03
Repository weight
Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.
The full marking
Every deduction below names the file or setting it came from.
Instructions 15/27 B-
Whether the repo tells an agent how to behave before it starts guessing.
✓Agent instruction file
12/12
AGENTS.md is present, which is the format the most tools read.
Also found: CLAUDE.md
✗Instruction quality
0/12
Present but too thin to change an agent's behavior.
Worth fixing: it's under 200 characters, which is closer to a placeholder than instructions; it never states a build, test, or run command; has no headings to structure it; has no code blocks.
✓README as an entry point
3/3
README has a clear getting-started section.
Setup 18/20 A
Whether an agent can install the project and get it running without a human.
✓Deterministic install
6/6
package-lock.json pins the dependency tree.
Found package-lock.json
✓Discoverable commands
6/6
Commands are declared where an agent will look for them.
Makefile
pyproject.toml scripts
scripts/ directory
✓Environment config
4/4
.env.example documents what the app needs to run.
✗Pinned runtime version
0/2
No pinned runtime version.
Add a .nvmrc, .python-version, or equivalent so the agent's toolchain matches yours.
✓Reproducible environment
2/2
.devcontainer/devcontainer.json gives a known-good environment.
Verification loop 24/25 A+
Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.
✓Tests exist
8/8
3965 test files against 7468 source files.
e.g. .github/workflows/helm_unit_test.yml, .github/workflows/mutation-test.yml, cookbook/litellm_router_load_test/test_loadtest_openai_client.py
✓Test command is discoverable
7/7
An agent can find and run `make test`.
✓Continuous integration
4/4
46 GitHub Actions workflows define what "passing" means.
✓Lint and format rules
3/3
ruff.toml encodes the house style.
✗Static type checking
2/3
Type checking is configured, but not in strict mode.
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
Context economy 9/20 C
Whether the repo fits in a context window, or fights it.
✓No committed build output
6/6
No generated directories committed.
✓.gitignore hygiene
3/3
.gitignore covers 124 patterns.
✗File sizes fit in context
0/6
119 source files are over 100KB.
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
ui/litellm-dashboard/src/lib/http/schema.d.ts — 2158KB
litellm/proxy/swagger/swagger-ui-bundle.js — 1451KB
litellm/proxy/proxy_server.py — 722KB
✗Repository weight
0/5
About 1476MB checked out. Large enough that cloning and searching are both slow.
Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.
Here is your AGENTS.md
Drafted from what is actually in this repository: the install
command from your lockfile, the commands you already declare, your real directory layout. Anything
marked TODO needs a person. Save it at the root as AGENTS.md.
# AGENTS.md 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] ## Setup ``` npm ci ``` ## Commands ``` make help make info make install-dev make bootstrap make install-proxy-dev make install-dev-ci ``` ## Layout - `tests/` 2911 source files - `litellm/` 2255 source files - `ui/` 1865 source files - `enterprise/` 149 source files - `litellm-rust/` 127 source files - `cookbook/` 38 source files ## Conventions - Tests live alongside the code they cover, following `.github/workflows/helm_unit_test.yml`. - CI defines what passing means. See `.github/workflows/_test-unit-base.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - `ui/litellm-dashboard/src/lib/http/schema.d.ts` is 2158KB. It will not fit comfortably in context, so read it in parts. - Copy `.env.example` before running anything that needs configuration. --- Drafted by agentreadme.com from what is in this repository. Everything marked TODO needs a human. Check it in as AGENTS.md at the root.
Open the raw markdown
or
curl -o AGENTS.md agentreadme.com/draft/BerriAI/litellm.md
Show the mark
The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.
[](https://agentreadme.com/BerriAI/litellm)Other Python repositories, marked
Think this mark is wrong?
Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.