Run several AI coding agents in parallel and their branches collide the moment you merge — and you find out one at a time, after every agent has finished.
Braidkeep predicts conflicts between in-flight branches using Git's own merge-tree (read-only, never touches your working tree), enforces per-agent file ownership, and computes a safe merge order: conflict-free batches first, tangles last.
Any orchestrator. Single binary, Apache-2.0, free. Predicts mergeability, not correctness.
Most continual-learning methods either forget (fine-tuning) or isolate and forfeit transfer (fixed masks, adapters). Coincidex does both: similar tasks share sub-networks for forward transfer, dissimilar ones stay isolated so old skills survive — with no replay buffer. A tiny, drop-in PyTorch layer (torch + numpy, CPU-friendly) that learns task similarity from context. It's also honest: reproducible benchmarks and a clear map of where it works and where it doesn't. Apache-2.0 license.
Most WebAssembly runtimes are general-purpose. Kelvane is built for one job: running a neural policy you don't fully trust. Every call runs in a fresh sandbox with a hard memory cap, a per-invocation CPU budget, and zero ambient authority (no files, network, or I/O). The model stays host-owned — the module asks for an inference but never touches the weights. You can hot-swap modules live. Honest scope: it's a small, tested integration of proven parts (Wasmtime, ONNX), not a new technique.
