Hey-Meadow/meadow-mind — 0 Stars
Zero training, second-level reactions (~400ms). A language-rule decision mind on a local 7B diffusion LM.
Watch Episode
About This Repo#
Hey-Meadow/meadow-mind — 0 ⭐
Zero training, second-level reactions (~400ms). A language-rule decision mind on a local 7B diffusion LM. - Hey-Meadow/meadow-mind
Narration#
An AI that learns to play games with zero training. Just one sentence of English. Meadow Mind — a language-rule decision system on a 7B diffusion model. No reinforcement learning, no gradients. One sentence policy, one sentence observation. Decides in 400 milliseconds — actual human reaction speed. CartPole: perfect 400 out of 400. It doesn’t generate tokens. It decides in one fixed-latency pass. AI that thinks like a reflex.
Watch#
DeusData/codebase-memory-mcp — 9,534 Stars
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms...
runtypelabs/persona — 16 Stars
Create agentic front-end experiences for the web in VanillaJS™️. Lightweight, extensible, and WebMCP-native.
Kong/insomnia — 39,389 Stars
The open-source, cross-platform API client for GraphQL, REST, WebSockets, SSE and gRPC. With Cloud, Local and Git storage.