Open Kioku turns a repository into an evidence layer: exact symbols, ranked context, impact, tests, history, architecture, and verification — so agents can plan from facts instead of guessing from file crawls.
The 3.0.4 release was tested end to end on a large Java repository, with the workload, timings, and caveats reported below.
The evidence below identifies the immutable Open Kioku 3.0.4 release, publishes aggregate results, and keeps caveats beside the claims they qualify.
A concise visual summary of the release identity, large-Java workload, and observed quality checks. The adjacent artifacts are the source of record.
The JSON records release source, host profile, configuration, command shapes, workload totals, measurements, quality checks, and limitations. Repository identity and revision are withheld, so exact replay is not claimed.
The repeated structural run reproduced identical totals, exact identities ranked first, and graph queries used indexed anchors. Missing compiler-grade SCIP evidence remained visible instead of being treated as present.
Open Kioku combines deterministic code intelligence with explainable retrieval signals. Exact repository facts do not get demoted by a fuzzy match.
Definitions, references, paths, and exact evidence stay authoritative. Heuristics can help retrieval without rewriting repository truth.
Ranked snippets, exact line ranges, impact, nearby tests, and caveats give the next agent step a bounded evidence set.
Optional semantic retrieval stays on-device and can use persistent approximate nearest-neighbor search while exact-flat remains the correctness oracle.
Co-change, churn, ownership, reviewer, provenance, renames, and similar-change signals are derived from bounded local Git history.
Validation candidates are selected from indexed tests and repository evidence before a change begins, not as an afterthought.
Plans define edit boundaries. Verification compares the actual changed files with those boundaries and reports evidence caveats.
Click through the same sequence an agent can use before, during, and after a repository change.
The default workflow is designed for local repository intelligence rather than a hosted code-index service.
Core search and evidence are stored under the repository’s local .ok/ data.
The MCP server provides evidence tools; source edits remain in the normal editor and agent workflow.
Default MCP security configuration includes network denial; local semantic search does not require a hosted embeddings API.
ok prove reports index and validation signals while intentionally omitting source snippets.
Install locally, build the repository index, then generate a plan from the task you actually care about.