|
Say it to a chip. No network, no model server. A YAML file of example commands becomes a 250 KB model and a C99 runtime. The chip reads a sentence and answers 
|
Will this model fit on this chip? Answers it before you flash. 31 boards, byte-exact memory from the real TFLite Micro runtime, native and in the browser. Quantization previews and a CI action.
|
Format-aware compression, without the expertise. Point it at your data. It writes the OpenZL description, trains a compressor, verifies the round trip byte for byte, and reports the savings against zstd and gzip. 
|
| nlohmann/json |  | JSON for Modern C++ |
| duckdb/duckdb |  | An analytical in-process SQL database |
| cathrynlavery/diagram-design |  | Editorial diagram design for coding agents, HTML and SVG |
| fmtlib/fmt |  | A modern formatting library for C++ |
| yhirose/cpp-httplib |  | A C++ header-only HTTP/HTTPS server and client library |
| livekit/agents |  | A framework for building realtime voice AI agents |
| cactus-compute/needle |  | 14MB foundation model for phones, wearables, smart home and robots |
| growthbook/growthbook |  | Open source feature flags, experimentation and product analytics |
| tailscale/tailcat |  | Like netcat, but over Tailscale's data plane |
| Serial-Studio/Serial-Studio |  | Telemetry dashboard for UART, BLE, MQTT, Modbus and CAN bus |
| Openpanel-dev/openpanel |  | Open-source web and product analytics, an alternative to Mixpanel |
| facebook/openzl |  | Format-aware lossless data compression from Meta |
| 0xShug0/audio.cpp |  | Pure C++ inference engine for audio models, powered by ggml |
Speech recognition and tool-calling models on embedded Linux boards, under 200 MB of RAM, no cloud round trip.
Mostly the memory arithmetic: what fits, what an ARMv7 core can hold in real time, and when the honest answer is that it does not.
