Call every LLM API like it's OpenAI 👉 github.com/BerriAI/litellm
Joined December 2022
- Tweets 992
- Following 180
- Followers 5,211
- Likes 1,052
76 Photos and videos
May 18
Join our Town Hall on Tuesday, May 19th from 7:30-8:30am PST for security updates, product updates, and roadmap.
Register here: forms.gle/GSegwaNRM3xBdhxYA
446
LiteLLM (YC W23) retweeted
May 16
We're open sourcing LiteLLM Agent Platform
Run Claude Code, Codex, Hermes or any coding agent in isolated K8s sandboxes
The agent never sees your real API keys.
Here's how 👇
13
34
234
16,316
LiteLLM (YC W23) retweeted
May 14
5️⃣ new things on LiteLLM Agent Platform
📋 Skills Page - manage attach agent skills
⚡ API Snippets - curl/python/js drawer in session view
🔧 EKS Watchdog - stuck sessions recover via pod DNS
🧹 Sandbox - dead pods killed instantly
🏥 Port Fix - fix node port resolution
1
2
535
LiteLLM (YC W23) retweeted
May 13
5️⃣ new things on LiteLLM Agent Platform
🎉 Skills Library - reusable prompts for agents
🚀 EKS Deployments - web worker in-cluster
💪 Sandboxes - faster replenish health checks
🔥 Sandboxes - active sessions preempt warm pods
🧹 Agents UI - sortable table paginated API
1
4
478
May 12
Join us next Monday, 5/18, at 7:30-8:30am PST for our May Town Hall.
For agenda and registration, please visit:
docs.litellm.ai/blog/may-tow…
1
2
317
LiteLLM (YC W23) retweeted
May 9
Today we are launching the @LiteLLM Agent Platform - a simple, self-hosted infrastructure platform for running multiple agents in production.
This is great for AI platform teams looking to enable their developers to ship agents without giving up control of their infra.
1
3
17
1,024
Apr 23
GPT-5.5 is now available on LiteLLM AI Gateway.
Improved token efficiency. Stronger conceptual clarity. Excels at long-horizon deliverables.
github.com/BerriAI/litellm/p…
2
973
Apr 22
CVE-2026-30623 (vulnerability via Anthropic's MCP SDK) has been fixed since v1.83.6-nightly. Please refer to our blog post for more details. docs.litellm.ai/blog/mcp-std…
1
1
2
891
Apr 22
If you find other vulnerabilities, please report it here - github.com/BerriAI/litellm/s… or email security@berri.ai
1
530
Apr 16
Opus 4.7 is live on LiteLLM AI Gateway.
More efficient tokens. Higher benchmark scores. Designed for complex, long-horizon work.
5
541
LiteLLM (YC W23) retweeted
Apr 9
5️⃣ new things @LiteLLM
💪 vertex_ai - normalize finish_reason enum to OpenAI spec
✅ dashscope - preserve cache_control for prompt caching
🎉 TogetherAI - add together_ai/gpt-oss-120b
🛠️ ModelInfo - expose reasoning effort fields
🚀 PromptGuard - new guardrail integration
1
6
840
Apr 6
We are hosting our April Town Hall this Friday, April 10th at 7:30am PST.
How to contribute: Add your thoughts to this ticket to help us shape the agenda - github.com/BerriAI/litellm/i…
536
LiteLLM (YC W23) retweeted
Apr 6
5️⃣ new things @LiteLLM
🐳 Docker - Signed GHCR releases
✅ MCP - fix tool name prefix check
🛠️ S3 - use prepped URL for sigv4 signed releases
🚀 Presidio - fix anonymize text alignment on input
⚡️ Prometheus - add 7m 10m latency buckets for long-running LLM Requests
1
1
3
761
LiteLLM (YC W23) retweeted
Apr 3
📣 Announcing @LiteLLM's April Townhall
Agenda:
- Product roadmap
- Reliability and security updates
- Open Q&A with the team
Register here: forms.gle/zyyHLhHEyWGo1A7K8
1
1
693
LiteLLM (YC W23) retweeted
Apr 2
5️⃣ new things @LiteLLM
🐳 Docker - All Pip NPM Docker deps now pinned
💪 Qohash - new Guardrail provider
🛠️ Teams - enforce TPM/RPM limits for members
🎉 Gemini - skip fetch for File API URLs
🧹 Azure - forward api_version on embeddings
1
3
877
LiteLLM (YC W23) retweeted
Mar 30
Popular AI gateway startup LiteLLM ditches controversial startup Delve techcrunch.com/2026/03/30/po…
7
6
51
20,540
LiteLLM (YC W23) retweeted
Mar 30
Update from us @LiteLLM, We will be partnering with @TrustVanta for its SOC-2 Type 2 and ISO 27001 recertification. Thank you to the Vanta team for their quick help!
We are also in the process of identifying 3rd party auditors to verify our compliance controls.
5
3
123
25,085
LiteLLM (YC W23) retweeted
Mar 27
Also @LiteLLM immediately went public, transparently, and is even doing a webinar, to talk about lessons learned.
I haven’t heard shit from aqua nor checkmarx. When they should be role models about how to handle incidents. Instead they show us what NOT to do.
12
25
321
27,320
LiteLLM (YC W23) retweeted
Mar 26
Fascinating seeing security companies are so much worse at responding to incidents than non-security companies
Both aqua and checkmarx didn’t do a good job. LiteLLM handled it much better. Curious!!
Mar 26
TeamPCP supply chain campaign scope expanded beyond initial reports with new CISA KEV entry and detection tools now available. Campaign timeline spans Feb 28 initial access through March 24 LiteLLM PyPI compromise.
#DFIR_Radar
9
19
202
22,545