vegaml ships a full open-source toolbelt: cascaded inference, calibration, MCP server
kalyan_kpl · x · 2026-10-16
The Apache-2.0 project vegaml (215 stars) shipped a full toolbelt in one week: CLI, HTTP/MCP servers, Docker, ONNX export and a torch-free MLX engine for Apple silicon. It turns frozen 0.8B/4B models into typed decisions — choices, 0-1 scores, probabilities — with calibrated probabilities, conformal answer sets and explicit abstain flags, plus a 0.8B→4B→human cascade, a calibrate() refit on 30 of your own labels, and LangChain/LangGraph integration.
More from coding & agent
- Marc Lou praises PostShiba, a cute indie alternative to AWS SES for email infra — marclou · 2026-10-16
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Wiring Pstack skills from a Grok bot into Hermes agent loops — alexcovo_eth · 2026-10-16
- past.dev launches long-term memory API for AI agents, tops BEAM public benchmark — thisiskp_ · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- mitsuhiko's AI agent solved multiplayer with PeerJS before he could explain it — mitsuhiko · 2026-10-16