LiteLLM
LiteLLM, developed by BerriAI, is an open-source library that standardizes API calls across multiple large language models.
Signal Radar
Five-axis snapshot of this entity's footprint
Mentions × Lab Attention
Weekly mentions (solid) and average article relevance (dotted)
Timeline
4- Research MilestoneJul 1, 2026
Production-readiness audit revealed 3 security gaps: fail-open resolver, unpinned servers, opt-in least-privilege
View source - Regulatory ActionApr 4, 2026
litellm@1.82.8 package was hijacked on PyPI through a compromised maintainer account
View source - Regulatory ActionApr 3, 2026
Compromised by malicious code inserted by the TeamPCP/Lapsus$ hacking group, leading to a widespread supply-chain attack affecting thousands of companies.
- compromise type:
- malicious code insertion
- distribution:
- PyPI package managers
- Product LaunchMar 24, 2026
Malicious version 1.38.2 of LiteLLM was uploaded to PyPI containing code to steal API keys and credentials
View source- version:
- 1.38.2
- compromised:
- true
Relationships
3Uses
Frequently appears with
3Entities that show up in the same articles — shared coverage, not a stated relationship.
Recent Articles
2Route Claude Code to DeepSeek for Cheap Tasks: The Two-Command Trust Split
+Use ANTHROPIC_BASE_URL and LiteLLM's drop_params to create a claude-cheap alias for DeepSeek, keeping your subscription for high-stakes work.
88 relevanceOpen-Weight Models Just Matched Claude Opus 4.6 — Here's How to Run Them
~Route Claude Code to open-weight models like Kimi K3 and DeepSeek V4 Flash via ANTHROPIC_BASE_URL or LiteLLM. Test cheap models before spending Opus 4
71 relevance
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.
Sentiment History
| Week | Avg Sentiment | Mentions |
|---|---|---|
| 2026-W27 | -0.10 | 1 |
| 2026-W32 | 0.20 | 1 |
| 2026-W34 | 0.30 | 1 |