** 에이전트에 대한 빠른 하이브리드 코드 검색.** Pure Go, 단일 정적 바이너리, Drop-in MCP-compatible with MinishLab/semble - 동일한 도구 스키마, 동일한 출력 형식, 이동 바이너리로 스왑 단계 설치.

ken은 복제의 이동 포트입니다 : BM25 lexical + Model2Vec semantic embeddings + RRF fusion + 코드 인식 reranker, 분산 알고리즘 ** verbatim ** semble의 search.py + ranking/*.py.

왜 켄

-~97% recall@10 (hybrid) 모드 — **0.967 NL / 0.995 기호 ** semble’s 1,251-query 벤치 마크에, 대 grep’s ~99.9% — 대리인을 요하는 동안 **~46× 몇몇 토큰 ** grep + Read (4,120 대 189,773 NL 쿼리에 미디어 토큰 - 동일한 기본 하이브리드 모드에서 측정). "이 대답하는 펑크를 정의,"는 1–2 주문-magnitude 토큰은 가까운 불평에 승리합니다. docs/BENCH.md.)

• ** 단일 정적 바이너리.** 순수 이동, cgo 없음, 추운 시작에 파이썬 해석기 없음, 색인에 GIL 없음. Linux / macOS / Windows (amd64 / arm64)에 크로스 컴파일.
• ** 럼블에 대한 드래그 인.** 동일한 search / find_related] MCP 도구 스키마 및 동일한 마크 다운 문자열 와이어 형식 - command:] 경로와 기존 에이전트가 변경되지 않는 교환을 교환합니다.

ken

ken is code search built for coding agents: a pure-Go, single-binary engine that runs a 16M-parameter Model2Vec model in-process, with no cgo, Python, vector database, or API key. On ContextBench (53 SWE-bench Pro tasks, 8k-token budget), its default hybrid mode covered 52% of the relevant files versus 29% for BM25 alone, and on tasks where a gold line was retrieved reached the first gold line in about 40% fewer tokens. Warm queries take a millisecond or two, and with KEN_ANN=flat-i8 the watched dense vector store uses about 80% less memory.

Fast hybrid code search for agents. Pure Go, single static binary, drop-in MCP-compatible with MinishLab/semble — same tool schemas, same output format, install steps swapped to a Go binary.

ken is a Go port of semble: BM25 lexical + Model2Vec semantic embeddings + RRF fusion + a code-aware reranker, with the retrieval algorithm ported verbatim from semble’s search.py + ranking/*.py.

Why ken

• ~97% recall@10 in the default (hybrid) mode — 0.967 NL / 0.995 symbol on semble’s 1,251-query benchmark, vs grep’s ~99.9% — while costing an agent ~46× fewer tokens than grep + Read (4,120 vs 189,773 median tokens on NL queries — measured in the same default hybrid mode). For “find the chunk that answers this,” that’s a 1–2 order-of-magnitude token win at near-parity recall. (Reproduce: docs/BENCH.md.)
• Single static binary. Pure Go, no cgo, no Python interpreter on cold start, no GIL on indexing. Cross-compiles to Linux / macOS / Windows (amd64/arm64) for free.
• Drop-in for semble. Same search / find_related MCP tool schemas and the same markdown-string wire format — swap the command: path and existing agents work unchanged.
• Local, CPU-only. Embedding inference, BM25, and fusion all run on the CPU. No API keys, no GPU, no vector DB, air-gapped friendly.