Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.
Research preservation
The official SWE-bench spike history is committed in this repository under the archive tag
archive/swebench-spikes-2026-09-26. The temporary archival branch was deleted. It is deliberately separate from the
maintained CLI and installed-package harness on main; do not merge its obsolete
runners or historical instructions into the product.
The immutable snapshot preserves all 358 previously untracked official research files at their original relative paths: experiment implementations, tests, native-agent harness variants, frozen configurations, prompts, result reports and analysis. The manifest records each file's SHA-256; every byte was verified against the local archive. No model calls, baseline reruns, or result recomputation accompanied preservation.
Reading the evidence
- Paired agent trace findings explain how baseline and retrieval-assisted agents explored the same tasks.
- Context findings record early handoff and output-consumption problems.
- Historical reports and source preserve alternatives, including failed and superseded experiments. Old model, timing, output and status statements describe their own studies, not the release.
- Retrieval lessons and the implementation record own the synthesis and final product evidence, including the failed original quality gates.
The snapshot is source history, not a promise that every old experiment runs from
a fresh clone. Raw responses, agent traces, baseline artifacts, source snapshots,
and evaluator datasets remain in ignored local evals/runs/swebench/ and
evals/runs/tooling/. Their recorded paths and hashes remain unchanged. These
large artifacts are not included in Git; losing that local storage would lose
evidence that cannot be recovered from the source snapshot alone.
Deprecated personal-repository evaluations are excluded from the public archive.
Their tooling, fixtures, and local archive were deleted at the user’s explicit
request. Official SWE-bench research and raw evidence remain preserved as described
above. Redundant .claude skill links were removed; canonical development skills
remain in .agents/skills/.