I had to make so many changes to mem0 to get it to work with litellm
November 3, 2025 at 7:14 PM
I had to make so many changes to mem0 to get it to work with litellm
I'd use Ollama + LiteLLM. If you like a Pythonic interface, I built LlamaBot github.com/ericmjl/llam.... Uses LiteLLM underneath the hood as a router to different model providers, Ollama included. Also tried deploying Ollama on @modal-labs.bsky.social ericmjl.github.io/blog/2024/11...
GitHub - ericmjl/llamabot: Pythonic class-based interface to LLMs
Pythonic class-based interface to LLMs. Contribute to ericmjl/llamabot development by creating an account on GitHub.
github.com
December 21, 2024 at 3:18 AM
I'd use Ollama + LiteLLM. If you like a Pythonic interface, I built LlamaBot github.com/ericmjl/llam.... Uses LiteLLM underneath the hood as a router to different model providers, Ollama included. Also tried deploying Ollama on @modal-labs.bsky.social ericmjl.github.io/blog/2024/11...
Benefits of Using LiteLLM for Your LLM Apps www.kdnuggets.com/benefits-...
July 23, 2025 at 10:00 PM
Benefits of Using LiteLLM for Your LLM Apps www.kdnuggets.com/benefits-...
litellmにcopilotのモデルサポートマージされてる
May 16, 2025 at 12:07 AM
litellmにcopilotのモデルサポートマージされてる
They're using LiteLLM to abstract the model access so it'll support a range of providers - likely list here:
github.com/i-dot-ai/red...
github.com/i-dot-ai/red...
April 28, 2025 at 11:14 AM
They're using LiteLLM to abstract the model access so it'll support a range of providers - likely list here:
github.com/i-dot-ai/red...
github.com/i-dot-ai/red...
📦 langfuse / langfuse
⭐ 2,407 (+38)
🗒 TypeScript
🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management 🍊YC W23 🤖 SDKs + integrations for Typescript, Python, OpenAI, Langchain, LlamaIndex, Litellm
⭐ 2,407 (+38)
🗒 TypeScript
🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management 🍊YC W23 🤖 SDKs + integrations for Typescript, Python, OpenAI, Langchain, LlamaIndex, Litellm
GitHub - langfuse/langfuse: 🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management 🍊YC W23 🤖 SDKs + integrations for Typescript, Python, OpenAI, Langchain, LlamaIndex, Litellm
🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management 🍊YC W23 🤖 SDKs + integrations for Typescript, Python, OpenAI, Langchain, LlamaIndex, Litellm - langfuse/lang...
github.com
March 19, 2024 at 12:50 PM
Tired of LLM Chaos? LiteLLM Should Be Your Default Last Updated on February 12, 2025 by Editorial...
https://towardsai.net/p/artificial-intelligence/tired-of-llm-chaos-litellm-should-be-your-default
#Artificial #Intelligence #Data #Science #Latest #Machine […]
[Original post on towardsai.net]
https://towardsai.net/p/artificial-intelligence/tired-of-llm-chaos-litellm-should-be-your-default
#Artificial #Intelligence #Data #Science #Latest #Machine […]
[Original post on towardsai.net]
February 12, 2025 at 6:28 PM
Tired of LLM Chaos? LiteLLM Should Be Your Default Last Updated on February 12, 2025 by Editorial...
https://towardsai.net/p/artificial-intelligence/tired-of-llm-chaos-litellm-should-be-your-default
#Artificial #Intelligence #Data #Science #Latest #Machine […]
[Original post on towardsai.net]
https://towardsai.net/p/artificial-intelligence/tired-of-llm-chaos-litellm-should-be-your-default
#Artificial #Intelligence #Data #Science #Latest #Machine […]
[Original post on towardsai.net]
OpenRouter, LiteLLM, Vercel’s AI SDK provide abstractions on top of multiple model providers. In enterprise, AWS Bedrock and Databricks do this as well. But models increasingly support different feature sets. Take Claude’s support for PDFs as an example docs.anthropic.com/en/docs/buil...
PDF support - Anthropic
Process PDFs with Claude 3.5 Sonnet. Extract text, analyze charts, and understand visual content from your documents.
docs.anthropic.com
December 20, 2024 at 6:54 PM
OpenRouter, LiteLLM, Vercel’s AI SDK provide abstractions on top of multiple model providers. In enterprise, AWS Bedrock and Databricks do this as well. But models increasingly support different feature sets. Take Claude’s support for PDFs as an example docs.anthropic.com/en/docs/buil...
Сьогодні через йобану русню не виспався, і пів дня проспав, а другу половину кодив для фрілансу.
Раніше я знайшов `litellm` лібу через яку можна будь яку LLM використовувати однаково, з нею в мене працював і ChatGPT, і Gemini і Ollama. Але була проблема, коли починаєш шось дебажити чи […]
Раніше я знайшов `litellm` лібу через яку можна будь яку LLM використовувати однаково, з нею в мене працював і ChatGPT, і Gemini і Ollama. Але була проблема, коли починаєш шось дебажити чи […]
Original post on twiukraine.com
twiukraine.com
April 18, 2025 at 3:51 PM
Сьогодні через йобану русню не виспався, і пів дня проспав, а другу половину кодив для фрілансу.
Раніше я знайшов `litellm` лібу через яку можна будь яку LLM використовувати однаково, з нею в мене працював і ChatGPT, і Gemini і Ollama. Але була проблема, коли починаєш шось дебажити чи […]
Раніше я знайшов `litellm` лібу через яку можна будь яку LLM використовувати однаково, з нею в мене працював і ChatGPT, і Gemini і Ollama. Але була проблема, коли починаєш шось дебажити чи […]
🚀 Just published: LiteLLM — Unified gateway for 100+ LLMs with spend tracking
Manage authentication, load balancing, and cost tracking across 100+ LLMs through a single OpenAI-compatible gateway. Trusted by Netflix and enterprise teams.
Manage authentication, load balancing, and cost tracking across 100+ LLMs through a single OpenAI-compatible gateway. Trusted by Netflix and enterprise teams.
LiteLLM
Unified gateway for 100+ LLMs with spend tracking
openalternative.co
July 31, 2025 at 2:00 PM
🚀 Just published: LiteLLM — Unified gateway for 100+ LLMs with spend tracking
Manage authentication, load balancing, and cost tracking across 100+ LLMs through a single OpenAI-compatible gateway. Trusted by Netflix and enterprise teams.
Manage authentication, load balancing, and cost tracking across 100+ LLMs through a single OpenAI-compatible gateway. Trusted by Netflix and enterprise teams.
I haven't been looking at their social media tbh. They broke my setup at work with litellm and the edit file tool. I fixed it and opened a PR. They closed today without reading and pissed me off.
Add `tool_call_none` setting by odellus · Pull Request #39969 · zed-industries/zed
Closes #ISSUE
Never opened issue. Just fixed it myself.
Release Notes:
Added a tool_call_none variable for setting to keep zed agent from sending mangled conversations to litellm, which does not e...
github.com
October 31, 2025 at 8:50 PM
I haven't been looking at their social media tbh. They broke my setup at work with litellm and the edit file tool. I fixed it and opened a PR. They closed today without reading and pissed me off.
for some reason litellm will ignore system prompts AND also ignore the one set in the litellm preset, very obnoxious
May 28, 2025 at 7:01 AM
for some reason litellm will ignore system prompts AND also ignore the one set in the litellm preset, very obnoxious
I finally have openwebui halfway instrumented through litellm and phoenix. Hallelujah. With search and follow up question just using deepseek-r1:8b through ollama I am impressed. Think it's ready to start making smart traversals of the human knowledge graph.
I basically tied myself to my computer until I got my website working the way I want it to. Then I broke it to try to make it better and now it's halfway there and it's time I unchain myself from my computer. I've always learned this way. Crunches.
July 29, 2025 at 6:23 AM
I finally have openwebui halfway instrumented through litellm and phoenix. Hallelujah. With search and follow up question just using deepseek-r1:8b through ollama I am impressed. Think it's ready to start making smart traversals of the human knowledge graph.
One that I recently saw and plan to setup is the Multi-Provider Generative AI Gateway solution. It's a production ready implementation of LiteLLM running inside AWS. You could set this up yourself but having a very flexible and configurable packing already built can really help. (3️⃣/3️⃣)
August 3, 2025 at 2:48 PM
One that I recently saw and plan to setup is the Multi-Provider Generative AI Gateway solution. It's a production ready implementation of LiteLLM running inside AWS. You could set this up yourself but having a very flexible and configurable packing already built can really help. (3️⃣/3️⃣)
- 📊 LlamaIndex: Connecting custom data to large language models
- 🧠 DSPy: Optimizing language model prompts and weights
- 📈 RAGAS: Evaluating Retrieval Augmented Generation (RAG) systems
- 🔄 LiteLLM: Unified interface for multiple LLM providers
- 🧠 DSPy: Optimizing language model prompts and weights
- 📈 RAGAS: Evaluating Retrieval Augmented Generation (RAG) systems
- 🔄 LiteLLM: Unified interface for multiple LLM providers
October 2, 2024 at 1:23 PM
- 📊 LlamaIndex: Connecting custom data to large language models
- 🧠 DSPy: Optimizing language model prompts and weights
- 📈 RAGAS: Evaluating Retrieval Augmented Generation (RAG) systems
- 🔄 LiteLLM: Unified interface for multiple LLM providers
- 🧠 DSPy: Optimizing language model prompts and weights
- 📈 RAGAS: Evaluating Retrieval Augmented Generation (RAG) systems
- 🔄 LiteLLM: Unified interface for multiple LLM providers
📦 Helicone / helicone
⭐ 2,287 (+81)
🗒 TypeScript
🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, Lang...
⭐ 2,287 (+81)
🗒 TypeScript
🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, Lang...
GitHub - Helicone/helicone: 🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. 🍓 YC W23
🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, ...
github.com
December 19, 2024 at 12:01 PM
Most people are probably well past this, but I just published a pretty simple AI playground kind of thing, based around Open-WebUI, backed by LiteLLM, Ollama, and SearXNG:
github.com/standaloneSA...
Maybe it will be useful for some people?
github.com/standaloneSA...
Maybe it will be useful for some people?
GitHub - standaloneSA/onprem-ai: On-prem config for docker-compose setup for AI studio
On-prem config for docker-compose setup for AI studio - standaloneSA/onprem-ai
github.com
February 16, 2025 at 9:01 PM
Most people are probably well past this, but I just published a pretty simple AI playground kind of thing, based around Open-WebUI, backed by LiteLLM, Ollama, and SearXNG:
github.com/standaloneSA...
Maybe it will be useful for some people?
github.com/standaloneSA...
Maybe it will be useful for some people?
ID: CVE-2024-5751
CVSS V3.0: CRITICAL
BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the `add_deployment` function, which decodes and decrypts environment variables from base64...
#security #infosec #cve-alert
CVSS V3.0: CRITICAL
BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the `add_deployment` function, which decodes and decrypts environment variables from base64...
#security #infosec #cve-alert
nvd.nist.gov
June 27, 2024 at 7:15 PM
ID: CVE-2024-5751
CVSS V3.0: CRITICAL
BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the `add_deployment` function, which decodes and decrypts environment variables from base64...
#security #infosec #cve-alert
CVSS V3.0: CRITICAL
BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the `add_deployment` function, which decodes and decrypts environment variables from base64...
#security #infosec #cve-alert
<a href="https://github.com/BerriAI/litellm" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">github.com/BerriAI/...
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 1...
- LLM APIをOpenAI形式で呼び出せるSDK、プロキシサーバー
- 100以上のLLMに対応し、予算やレート制限も可能
- ログ出力、プロキシキー管理などの機能も持つ
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 1...
- LLM APIをOpenAI形式で呼び出せるSDK、プロキシサーバー
- 100以上のLLMに対応し、予算やレート制限も可能
- ログ出力、プロキシキー管理などの機能も持つ
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
github.com
March 21, 2025 at 2:56 AM
<a href="https://github.com/BerriAI/litellm" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">github.com/BerriAI/...
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 1...
- LLM APIをOpenAI形式で呼び出せるSDK、プロキシサーバー
- 100以上のLLMに対応し、予算やレート制限も可能
- ログ出力、プロキシキー管理などの機能も持つ
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 1...
- LLM APIをOpenAI形式で呼び出せるSDK、プロキシサーバー
- 100以上のLLMに対応し、予算やレート制限も可能
- ログ出力、プロキシキー管理などの機能も持つ
🔥 Bespoke curator: Synthetic Data Curation for Post-Training & Structured Data Extraction
Create synthetic data pipelines with easy!
- Retries and caching included
- inference via LiteLLM, vLLM, and popular batch APIs
- asynchronous operations
🔗 URL: buff.ly/ajPRT1l
Create synthetic data pipelines with easy!
- Retries and caching included
- inference via LiteLLM, vLLM, and popular batch APIs
- asynchronous operations
🔗 URL: buff.ly/ajPRT1l
April 10, 2025 at 12:00 PM
🔥 Bespoke curator: Synthetic Data Curation for Post-Training & Structured Data Extraction
Create synthetic data pipelines with easy!
- Retries and caching included
- inference via LiteLLM, vLLM, and popular batch APIs
- asynchronous operations
🔗 URL: buff.ly/ajPRT1l
Create synthetic data pipelines with easy!
- Retries and caching included
- inference via LiteLLM, vLLM, and popular batch APIs
- asynchronous operations
🔗 URL: buff.ly/ajPRT1l
📦 /BerriAI/litellm
🔗 https://github.com/BerriAI/litellm
⭐ Stars: 14754 🍴 Forks:1729
#python
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Huggi
🔗 https://github.com/BerriAI/litellm
⭐ Stars: 14754 🍴 Forks:1729
#python
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Huggi
GitHub - BerriAI/litellm: Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq] - BerriAI/litellm
github.com
December 7, 2024 at 5:29 AM
📦 /BerriAI/litellm
🔗 https://github.com/BerriAI/litellm
⭐ Stars: 14754 🍴 Forks:1729
#python
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Huggi
🔗 https://github.com/BerriAI/litellm
⭐ Stars: 14754 🍴 Forks:1729
#python
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Huggi
<a href="https://zenn.dev/loglass/articles/bfb92ed1e7d012" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">zenn.dev/loglass/ar...
LLM APIを良い感じに呼べればOKな時に便利なlitellm
LLM APIを良い感じに呼べればOKな時に便利なlitellm
LLM APIを良い感じに呼べればOKな時に便利なlitellm
! この記事は毎週必ず記事がでるテックブログ "Loglass Tech Blog Sprint"の25週目の記事です！ 1年間連続達成まで 残り28週 となりました！ こんにちは。ログラスのLLMチームでソフトウェアエンジニアをしている r-kagaya です。…
zenn.dev
February 10, 2024 at 10:06 PM
<a href="https://zenn.dev/loglass/articles/bfb92ed1e7d012" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">zenn.dev/loglass/ar...
LLM APIを良い感じに呼べればOKな時に便利なlitellm
LLM APIを良い感じに呼べればOKな時に便利なlitellm
Found at “LiteLLM” on 2025-03-06 13:10:38 +01:00.
> LLM Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the **OpenAI format**.
> LLM Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the **OpenAI format**.
March 19, 2025 at 3:56 PM
Found at “LiteLLM” on 2025-03-06 13:10:38 +01:00.
> LLM Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the **OpenAI format**.
> LLM Gateway to provide model access, fallbacks and spend tracking across 100+ LLMs. All in the **OpenAI format**.
📦 langfuse / langfuse
⭐ 12,862 (+33)
🗒 TypeScript
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
⭐ 12,862 (+33)
🗒 TypeScript
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
GitHub - langfuse/langfuse: 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ...
github.com
June 21, 2025 at 2:02 PM