All things free AI & tokens — as it happens.
120 signals from Hacker News and the open-source release feeds we track. Auto-refreshed every few hours. No algorithm, no ads — just what's new in $0 AI.
-
Demucs v4.0.1
SOTA open stem separation (MIT)
-
Langfuse v4.35.0
Open LLM tracing, evals, prompt mgmt
-
n8n n8n@2.38.7
Self-host workflow automation
-
LiteLLM v1.100.1
One proxy for 100+ model providers
-
Dify 1.17.1
Open LLM app / RAG builder
-
ComfyUI v0.35.0
Node-based gen-media workflow engine
-
Unsloth v0.1.808-beta
2× faster QLoRA on a free T4
-
vLLM v0.29.0
High-throughput open inference server
-
Ollama v0.34.0
Run open models locally, unmetered
-
llama.cpp v0.4.0
CPU/Metal inference for GGUF models
-
MCP Servers 2026.8.31
Official reference MCP tool servers
-
llama.cpp b9627
CPU/Metal inference for GGUF models
-
vLLM v0.23.0
High-throughput open inference server
-
llama.cpp b9616
CPU/Metal inference for GGUF models
No signals match that filter.