LiteLLM (YC W23)

Call every LLM API like it's OpenAI 👉

[LiteLLM (YC W23) @LiteLLM]

Join our Town Hall on Tuesday, May 19th from 7:30-8:30am PST for security updates, product updates, and roadmap.

Register here: https://t.co/Q6PbTtQTYc

[Ishaan @ishaan_jaff]

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 👇

[Krrish @krrish_dh]

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

[Krrish @krrish_dh]

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

[LiteLLM (YC W23) @LiteLLM]

Join us next Monday, 5/18, at 7:30-8:30am PST for our May Town Hall.

For agenda and registration, please visit:

https://t.co/LEcLXyhCPO

[Ishaan @ishaan_jaff]

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.

[LiteLLM (YC W23) @LiteLLM]

GPT-5.5 is now available on LiteLLM AI Gateway.

Improved token efficiency. Stronger conceptual clarity. Excels at long-horizon deliverables.
https://t.co/umxktNZhOI

[LiteLLM (YC W23) @LiteLLM]

If you find other vulnerabilities, please report it here - https://t.co/QcFcPW66Nk or email [email protected]

[LiteLLM (YC W23) @LiteLLM]

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. https://t.co/ImGk2mGYug

[LiteLLM (YC W23) @LiteLLM]

🔗 Blog post: https://t.co/ImGk2mGYug

[LiteLLM (YC W23) @LiteLLM]

Opus 4.7 is live on LiteLLM AI Gateway.

More efficient tokens. Higher benchmark scores. Designed for complex, long-horizon work.

[Krrish @krrish_dh]

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

[LiteLLM (YC W23) @LiteLLM]

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 - https://t.co/DTTMltSok0

[LiteLLM (YC W23) @LiteLLM]

@SandySwipe @SethDeGroot Thanks @SandySwipe! We'll be hosting a public Town Hall on Friday, 4/10 as well: https://t.co/kcA9K1fQzg

[LiteLLM (YC W23) @LiteLLM]

@kshitizh @mercor_ai Sharing links to our Security Update: https://t.co/wWeHmo7e0n and Town Hall: https://t.co/jcoOff7Nmp

[LiteLLM (YC W23) @LiteLLM]

@building_KR @krrish_dh Hi @building_KR, appreciate the support! We are looking at April 11th

[Krrish @krrish_dh]

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

[Krrish @krrish_dh]

📣 Announcing @LiteLLM's April Townhall

Agenda:
- Product roadmap
- Reliability and security updates
- Open Q&A with the team

Register here: https://t.co/nbdfggyUCI

[Krrish @krrish_dh]

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

[LiteLLM (YC W23) @LiteLLM]

@shahin43 @garrytan @mercor_ai Sharing the updates from our public Town Hall: https://t.co/jcoOff7Nmp