observers 🔭 - automatically log all OpenAI compatible requests to a dataset 💽
• supports any OpenAI compatible endpoint 💪
• supports @duckdb.org, @huggingface.bsky.social datasets and Argilla as stores
> pip install observers
• supports any OpenAI compatible endpoint 💪
• supports @duckdb.org, @huggingface.bsky.social datasets and Argilla as stores
> pip install observers
November 21, 2024 at 8:06 PM
observers 🔭 - automatically log all OpenAI compatible requests to a dataset 💽
• supports any OpenAI compatible endpoint 💪
• supports @duckdb.org, @huggingface.bsky.social datasets and Argilla as stores
> pip install observers
• supports any OpenAI compatible endpoint 💪
• supports @duckdb.org, @huggingface.bsky.social datasets and Argilla as stores
> pip install observers
DEEPSEEK V4 FLASH AND PRO SPOTTED ON DEEKSEEK DOCS. THIS IS NOT A DRILL
Your First API Call | DeepSeek API Docs
The DeepSeek API uses an API format compatible with OpenAI/Anthropic. By modifying the configuration, you can use the OpenAI/Anthropic SDK or softwares compatible with the OpenAI/Anthropic API to acce...
api-docs.deepseek.com
April 24, 2026 at 3:18 AM
DEEPSEEK V4 FLASH AND PRO SPOTTED ON DEEKSEEK DOCS. THIS IS NOT A DRILL
"openai hears rumors of this problem being solvable -> huge internal effort that initially doesn't get there -> desperate researcher retrieves conversations and guides the model with them" is compatible with the account ("no *model* access/lookup, but no other denials) and also very ugly for OpenAI
September 8, 2026 at 7:18 AM
"openai hears rumors of this problem being solvable -> huge internal effort that initially doesn't get there -> desperate researcher retrieves conversations and guides the model with them" is compatible with the account ("no *model* access/lookup, but no other denials) and also very ugly for OpenAI
September 5, 2026 at 1:56 AM
Lettabot now has an OpenAI-compatible completions endpoint.
Any client that works with OpenAI (Open WebUI, LangChain, LibreChat, the openai SDK, etc.) works directly with Lettabot now.
Please try it out, lmk if you find bugs.
14 PRs merged in this release.
Any client that works with OpenAI (Open WebUI, LangChain, LibreChat, the openai SDK, etc.) works directly with Lettabot now.
Please try it out, lmk if you find bugs.
14 PRs merged in this release.
February 24, 2026 at 1:14 AM
Lettabot now has an OpenAI-compatible completions endpoint.
Any client that works with OpenAI (Open WebUI, LangChain, LibreChat, the openai SDK, etc.) works directly with Lettabot now.
Please try it out, lmk if you find bugs.
14 PRs merged in this release.
Any client that works with OpenAI (Open WebUI, LangChain, LibreChat, the openai SDK, etc.) works directly with Lettabot now.
Please try it out, lmk if you find bugs.
14 PRs merged in this release.
I wanted to run @cocore.dev on my AMD strix-halo machine that I use for local AI inference, but I saw that they only had an Apple-MLX engine. So I added an OpenAI-compatible HTTP engine + linux support, and you can point it to your local llama-server/ollama/vllm/etc.
github.com/graze-social...
github.com/graze-social...
Add an OpenAI-compatible HTTP engine + make the agent build on Linux by bmv437 · Pull Request #86 · graze-social/cocore
Today the only backend that does real inference is Apple-MLX, so a provider has to be a Mac. This PR adds an engine that just talks to any OpenAI-compatible endpoint over HTTP/HTTPS (such ash llama...
github.com
June 23, 2026 at 4:53 AM
I wanted to run @cocore.dev on my AMD strix-halo machine that I use for local AI inference, but I saw that they only had an Apple-MLX engine. So I added an OpenAI-compatible HTTP engine + linux support, and you can point it to your local llama-server/ollama/vllm/etc.
github.com/graze-social...
github.com/graze-social...
Access stateful agents through any OpenAI-compatible interface.
Run `letta server --openai-api` to chat with stateful agents through
OpenWebUI, LibreChat, & more.
Run `letta server --openai-api` to chat with stateful agents through
OpenWebUI, LibreChat, & more.
July 28, 2026 at 8:03 PM
Access stateful agents through any OpenAI-compatible interface.
Run `letta server --openai-api` to chat with stateful agents through
OpenWebUI, LibreChat, & more.
Run `letta server --openai-api` to chat with stateful agents through
OpenWebUI, LibreChat, & more.
TIL open-webui — an open source ChatGPT environment that supports ollama & openai-compatible APIs
h/t @simonwillison.net for finding it
github.com/open-webui/o...
h/t @simonwillison.net for finding it
github.com/open-webui/o...
GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui
github.com
January 20, 2025 at 10:17 PM
TIL open-webui — an open source ChatGPT environment that supports ollama & openai-compatible APIs
h/t @simonwillison.net for finding it
github.com/open-webui/o...
h/t @simonwillison.net for finding it
github.com/open-webui/o...
One of the quickest ways to start playing with a good local LLM on macOS (if you have ~12GB free disk/RAM) - using llama-server and gpt-oss-20b:
brew install llama.cpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF \
--ctx-size 0 --jinja -ub 2048 -b 2048 -ngl 99 -fa
simonwillison.net/2025/Aug/19/...
brew install llama.cpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF \
--ctx-size 0 --jinja -ub 2048 -b 2048 -ngl 99 -fa
simonwillison.net/2025/Aug/19/...
llama.cpp guide: running gpt-oss with llama.cpp
Really useful official guide to running the OpenAI gpt-oss models using llama-server from llama.cpp - which provides an OpenAI-compatible localhost API and a neat web interface for interacting with th...
simonwillison.net
August 19, 2025 at 7:47 PM
One of the quickest ways to start playing with a good local LLM on macOS (if you have ~12GB free disk/RAM) - using llama-server and gpt-oss-20b:
brew install llama.cpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF \
--ctx-size 0 --jinja -ub 2048 -b 2048 -ngl 99 -fa
simonwillison.net/2025/Aug/19/...
brew install llama.cpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF \
--ctx-size 0 --jinja -ub 2048 -b 2048 -ngl 99 -fa
simonwillison.net/2025/Aug/19/...
Most inference engines make you choose between throughput and memory efficiency.
vLLM skips that tradeoff:
• OpenAI-compatible API
• Wide model support
• Built for speed on real hardware
Just added to OpenAlternative 👇
openalternative.co/vllm
vLLM skips that tradeoff:
• OpenAI-compatible API
• Wide model support
• Built for speed on real hardware
Just added to OpenAlternative 👇
openalternative.co/vllm
vLLM: Open Source Alternative to Together AI and Fireworks AI
Inference and serving engine for large language models, built for speed and hardware efficiency with an OpenAI-compatible API and support for a wide range of…
openalternative.co
September 24, 2026 at 11:59 AM
Most inference engines make you choose between throughput and memory efficiency.
vLLM skips that tradeoff:
• OpenAI-compatible API
• Wide model support
• Built for speed on real hardware
Just added to OpenAlternative 👇
openalternative.co/vllm
vLLM skips that tradeoff:
• OpenAI-compatible API
• Wide model support
• Built for speed on real hardware
Just added to OpenAlternative 👇
openalternative.co/vllm
¡Un agente de IA para programar desde tu terminal!
Se llama OpenCode y es una alternativa a Claude Code.
✓ 100% Open Source
✓ Puedes usarlo con modelos locales
✓ Compatible con Copilot, OpenAI, Anthropic, Google...
→ github.com/sst/opencode
Se llama OpenCode y es una alternativa a Claude Code.
✓ 100% Open Source
✓ Puedes usarlo con modelos locales
✓ Compatible con Copilot, OpenAI, Anthropic, Google...
→ github.com/sst/opencode
September 16, 2025 at 12:55 PM
¡Un agente de IA para programar desde tu terminal!
Se llama OpenCode y es una alternativa a Claude Code.
✓ 100% Open Source
✓ Puedes usarlo con modelos locales
✓ Compatible con Copilot, OpenAI, Anthropic, Google...
→ github.com/sst/opencode
Se llama OpenCode y es una alternativa a Claude Code.
✓ 100% Open Source
✓ Puedes usarlo con modelos locales
✓ Compatible con Copilot, OpenAI, Anthropic, Google...
→ github.com/sst/opencode
to uphold the grand tradition of transsexual shoplifting i'm making an openai-compatible api router to round-robin a bunch of free-tier keys so i can mooch off the metered grace of corps ≈forever
January 16, 2026 at 5:24 PM
to uphold the grand tradition of transsexual shoplifting i'm making an openai-compatible api router to round-robin a bunch of free-tier keys so i can mooch off the metered grace of corps ≈forever
but is the spacex xai ai api compatible with the openai ai api? can I use openai ai api openapi clients with spacex xai ai api openapi endpoints?
September 10, 2026 at 10:03 PM
but is the spacex xai ai api compatible with the openai ai api? can I use openai ai api openapi clients with spacex xai ai api openapi endpoints?
🔥 AI dev tip
Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API
The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests
Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API
The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests
July 9, 2025 at 6:46 PM
🔥 AI dev tip
Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API
The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests
Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API
The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests
sorry, bring your own key. it works with any openai-compatible API.
March 31, 2026 at 3:13 AM
sorry, bring your own key. it works with any openai-compatible API.
Free LLM API — 820 models across 48 providers, behind one OpenAI-compatible key. 7.4 billion free tokens per month, tracked in one live catalog.
Free LLM API — every free model behind one key | FreeLLMAPI
A free LLM API: one OpenAI-compatible key for 600+ models across 34 providers, 7.4 billion free tokens per month, tracked in one live catalog.
freellmapi.co
September 26, 2026 at 1:00 AM
Free LLM API — 820 models across 48 providers, behind one OpenAI-compatible key. 7.4 billion free tokens per month, tracked in one live catalog.
Oh man, expose an OpenAI compatible API that connects you with another person at random and you can just chat with each other.
May 17, 2026 at 9:50 AM
Oh man, expose an OpenAI compatible API that connects you with another person at random and you can just chat with each other.
We've been hard at work since launching database.build, and we're thrilled to unveil a lineup of new features:
- Bring-your-own-LLM
- OpenAI compatibility
- CORS-friendly APIs
- Service workers
- Live Share
- Deployments
- Mobile Support
supabase.com/blog/databas...
- Bring-your-own-LLM
- OpenAI compatibility
- CORS-friendly APIs
- Service workers
- Live Share
- Deployments
- Mobile Support
supabase.com/blog/databas...
database.build v2: Bring-your-own-LLM
Use any OpenAI API compatible LLMs in database.build
supabase.com
December 6, 2024 at 3:22 PM
We've been hard at work since launching database.build, and we're thrilled to unveil a lineup of new features:
- Bring-your-own-LLM
- OpenAI compatibility
- CORS-friendly APIs
- Service workers
- Live Share
- Deployments
- Mobile Support
supabase.com/blog/databas...
- Bring-your-own-LLM
- OpenAI compatibility
- CORS-friendly APIs
- Service workers
- Live Share
- Deployments
- Mobile Support
supabase.com/blog/databas...
Tout ceci parait bien compatible avec une grosse séquence de lobbying pour une regulation des modèles, visant à exclure de fait les modèles ouverts, car "trop dangereux". Et donc restreindre l'offre à une poignée d'acteurs comme. par exemple, OpenAI ou Anthropic.
(surprise 🥳)
(surprise 🥳)
September 13, 2026 at 10:08 AM
Tout ceci parait bien compatible avec une grosse séquence de lobbying pour une regulation des modèles, visant à exclure de fait les modèles ouverts, car "trop dangereux". Et donc restreindre l'offre à une poignée d'acteurs comme. par exemple, OpenAI ou Anthropic.
(surprise 🥳)
(surprise 🥳)
good stuff. does this just use the completions api, i.e. can i point it at any completions (openai) compatible inference endpoint?
October 10, 2025 at 6:28 AM
good stuff. does this just use the completions api, i.e. can i point it at any completions (openai) compatible inference endpoint?
Is OpenAI going to rewrite all their software since these Broadcom chips presumably won't be compatible with CUDA? Can Broadcom even deliver a working software stack? Apparently AMD can't, and they're years ahead.
September 5, 2025 at 3:11 AM
Is OpenAI going to rewrite all their software since these Broadcom chips presumably won't be compatible with CUDA? Can Broadcom even deliver a working software stack? Apparently AMD can't, and they're years ahead.
