Files
John SmithandClaude Opus 5.5 3a6d104fcf chore(data): backfill kind, topics and compat for every entry; follow renamed repos
- kind/topics: keyword first pass, then reviewed and corrected by hand for all 513 entries
- compat: detected from npm packages, package.json and source (scripts/utils/compat.js). Plugins: 134 v2, 125 v1, 12 unverified; 13 entries the review loop marked V2 pin @opencode-ai/plugin 1.x, and ~20 loop V2 verdicts based only on the absence of V1 markers are V1 plugin functions in source
- npm and path filled where verifiable (package repository matches the entry); 9 bogus npm values from install prose were not kept
- 29 repo URLs updated to the renamed/transferred repository; xberg-io entries point at their live repos instead of the archived monorepo; lavi uses repo + path instead of a /tree/ URL
- removed projects/opencode-sessions.yaml (same repo as plugins/opencode-sessions.yaml)
- install: renamed to installation:, mojibake fixed, inline HTML links removed from two descriptions

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-17 13:00:22 -04:00

73 lines
2.1 KiB
YAML

name: OpenCode Indexing
repo: https://github.com/Javierkaiser/opencode-indexing
homepage: https://github.com/Javierkaiser/opencode-indexing#readme
tagline: Semantic code search for OpenCode that reuses Kilo Code's index and keeps its own incremental one.
description: |-
Adds semantic (vector) code search to OpenCode. It reads Kilo Code's existing
index (Qdrant ws-* collections and Kilo's local LanceDB) without ever modifying
it, and can import those vectors and chunks at zero embedding cost, then keep
its own incremental index (Qdrant oc-* collections or embedded LanceDB) keyed
on a per-file SHA-256. Search merges results from both indexes, so semantic
search keeps working even when Kilo is not installed, is disabled, or its index
is stale.
- Reuse Kilo Code's index read-only, importing vectors without re-embedding
- Own incremental index with manifest-based freshness (new/changed/deleted only)
- Vector-store agnostic: Qdrant or embedded LanceDB
- Settings and index actions from the TUI, Desktop and web clients
- Supported embedding providers: Mistral, OpenAI, Ollama, Gemini, Voyage,
OpenRouter and any OpenAI-compatible endpoint
kind: plugin
topics:
- code-intel
compat: v2
scope:
- global
tags:
- semantic-search
- code-search
- indexing
- embeddings
- qdrant
- lancedb
min_version: 2.0.0
installation: |
## Prerequisites
- OpenCode v2 (plugin API `@opencode/plugin` 2.x)
- Node.js >= 22.6
- Optional: a Qdrant server and/or the `@lancedb/lancedb` module
## Installation
### Installer (recommended, cross-platform)
```bash
# Linux / macOS
./install.sh
# Windows
powershell -ExecutionPolicy Bypass -File .\install.ps1
# any platform (the wrappers call this)
node install.mjs
```
### From npm
```bash
npm install @javierkaiser/opencode-indexing
```
Then reference it from `opencode.json`:
```jsonc
{
"plugins": [
{ "package": "@javierkaiser/opencode-indexing" }
]
}
```
## Configuration
Settings live in `~/.config/opencode/indexing.json` and are editable from
`/indexing-config` (any client) or the `/indexing` page (terminal TUI).