5 projects
manyagent
Wrap installed coding-agent CLIs; capture traces, curate cross-session knowledge, serve a read-only viewer.
snapshot-tool
Snapshot testing tool for ASV benchmarks - captures and compares function outputs to verify correctness after optimizations
fc-eval
A fork of Terminal-bench for evaluating FormulaCode.
fc-data
Python toolchain for building and maintaining FormulaCode benchmark tasks.
tacc-inf
Efficient LLM inference on Slurm clusters using vLLM (for TACC).
