Harness Hub
All open source

LiteLLM

Call any LLM with one interface — the model gateway.

BerriAI/litellm

Maintained by BerriAI

LiteLLM normalizes 100+ providers behind the OpenAI API format with a proxy server for routing, budgets, rate limits and observability. A quiet but essential piece of most production harnesses.

View on GitHubDocs

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • DocsOne OpenAI-compatible SDK and gateway for 100+ LLM APIs; frameworks such as Google ADK and CrewAI build on it.[1][2]
  • User reportsTeams have moved to it from framework-native clients for multi-provider access.[1]
  • MetadataVery active: v1.106.6 was released Oct 28, 2026.[1]

Cons

  • DocsIts packages have been compromised twice. In March 2026, PyPI 1.82.7 and 1.82.8 carried a credential stealer. On Oct 21, 2026, a malicious v1.107.0 went out to PyPI, Docker Hub and GHCR for 2-3 hours.[1][2]
  • User reportsAfter the second compromise, users complained that litellm.ai itself showed no notice of it.[1][2]
  • MetadataThe license is mixed: the enterprise/ directory is under a separate commercial license, and the rest is MIT.[1]
  • MetadataA very large backlog of about 1,709 open issues.[1]
  • User reportsUsers note that pinning older versions for safety means losing support for new model releases.[1]
Best for
Teams that need one interface and gateway across many LLM providers and can enforce strict dependency hygiene.
Watch out for
Pin exact, hash-verified versions, and rotate secrets if you installed 1.82.7, 1.82.8 or 1.107.0.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Activity

Last push
· today
Latest release
v1.108.14
· yesterday
Last 90 days
20+ releases
  1. v1.108.141.108.14 (LTS)

    · yesterday

    [!TIP] The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch Verify this release Same command for litellm-database, litellm-non_root and the docker.io/litellm/ images What's new in 1.108.14 (LTS) 3 PRs. 1…

  2. v1.111.0-rc.3Pre-release

    · yesterday

    Verify this release Same command for litellm-database, litellm-non_root and the docker.io/litellm/ images What's new in 1.111.0-rc.3 15 PRs. 11 fixed. No action needed to upgrade Changes Anthropic: Fixed temperature=1 returning 400 on Claude models that removed sampling params…

  3. v1.106.12

    · yesterday

    Verify this release Same command for litellm-database, litellm-non_root and the docker.io/litellm/ images What's new in 1.106.12 6 PRs. 2 fixed, 2 changed. No action needed to upgrade Changes Caching: Fixed GPT-6.2 system prompts missing the prompt cache on /v1/chat/completions…

  4. v1.110.2

    · yesterday

    Verify this release Same command for litellm-database, litellm-non_root and the docker.io/litellm/ images What's new in 1.110.2 11 PRs. 8 fixed. No action needed to upgrade Changes Anthropic: Fixed temperature=1 returning 400 on Claude models that removed sampling params on…

  5. v1.108.131.108.13 (LTS)

    · yesterday

    [!TIP] The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch Verify this release Same command for litellm-database, litellm-non_root and the docker.io/litellm/ images What's new in 1.108.13 (LTS) 7 PRs. 5…

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

The team behind it

The gateway between your harness and every model provider.

BerriAI builds LiteLLM — the open-source proxy that normalizes 100+ LLM providers behind the OpenAI API with routing, budgets and observability. A quiet standard inside production agent stacks.

3 pros · 4 cons

In research (1)

Featured

openclaw/openclaw

The viral open-source personal AI assistant that really does things.

Maintained by OpenClaw Foundation

v2026.11.6released
4 pros · 4 cons

mattpocock/skills

Small, composable agent skills for real engineering work.

Maintained by Matt Pocock (AI Hero)

4 pros · 4 cons

obra/superpowers

An agentic skills framework and software methodology that works.

Maintained by Jesse Vincent (obra)

4 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintained by · 1

Built on it · 4

Similar entries · 3

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.