Digamma: A lightweight Scheme dialect for AI workflows released
Understand this story
packetlost has released Digamma, a lightweight Scheme dialect for AI workflow automation. It comes with a self-hosting compiler and an LLVM ORC-based JIT backend that can compile Scheme expressions into native code on demand. The project is released under the BSD 2-Clause license, with prebuilt images available on Docker Hub. Its API requires setting the GOOGLE_CLOUD_PROJECT environment variable or explicitly passing a parameter, and the default value of GOOGLE_CLOUD_LOCATION is us-central1.
AI overview based on source reports · Updated 7 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIDigamma: A lightweight, JIT compiled Scheme for AI workflows
Digamma is a lightweight Scheme dialect for AI workflow automation with a self-hosted compiler, LLVM ORC JIT backend, concurrent mark-sweep GC, and ARM64 TBI tagged pointers, prioritizing execution efficiency and Lisp extensibility over strict RnRS compliance. It offers fiber-based concurrency with async I/O and networking, plus non-blocking Vertex AI (Gemini) and Dialogflow CX integration via asio-grpc, and supports hygienic macros (syntax-case and syntax-rules). Preliminary Gambit benchmark results on Raspberry Pi 5 show Nanos recording the fastest wall-clock time in 25 of 30 benchmarks against Ypsilon 2.0.9 and Guile 3.0.10.
Activity for this story
- Current comparable activity
- 8
- Peak comparable activity
- 10Nov 18 03:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.