kolkrabbi

Open-source AI coding agent for the terminal that works with several subscriptions in one session: your Claude Pro/Max, ChatGPT Plus/Pro (Codex) and GitHub Copilot through each vendor's own CLI, any OpenRouter model, or local Ollama/vLLM. Pauses and resumes on a limit, or continues on your next plan. One static Go binary, no telemetry

A new way for AI to search for data

View on GitHub

2GitHub stars

593commits on main

1forks

v1.3.7latest release, 2026-10-07

Go 92.8%, HTML 3.5%, Shell 3%, CSS 0.5% · created 2026-08-22 · last push 2026-10-08

What XERJ indexed

Snapshot

1,282 files · 10.0 MB

The whole repository at commit c40eb018fa. It is the newest commit on main.

Selected work

franco michetti
@onembyte

Licence

The repository

Apache-2.0

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

Apache-2.0, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

ai-agentai-codingclaude-code-alternativeclicoding-agentdeveloper-toolsgogolang

Example questions

How does kolkrabbi implement ai-agent?
Show the ai-coding code in kolkrabbi.

Inside the indexed corpus

1,282 files, 10.0 MB in total, about 8.0 KB per file.
Languages by size: Go 92.8%, HTML 3.5%, Shell 3%, CSS 0.5%, Makefile 0.1%.
On GitHub since 2026-08-22, last push 2026-10-08, 593 commits on main.

Licence on GitHub and in the corpus

GitHub reported Apache-2.0 for onembyte/kolkrabbi on 2026-10-31, and the LICENSE file at commit c40eb018fa was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

franco michetti (@onembyte) has 4 selected repositories on the hub.

Their other repository pages: tangency-labs/solidcraft, onembyte/alpheus, onembyte/Skeldri.

Using XERJ with kolkrabbi

A local search tool for Codex and Cursor kolkrabbi is tagged ai-coding on GitHub.
Local code search MCP that uses fewer tokens than grep
RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
ripgrep vs a code index for coding agents: 30 tasks

The prompt

Paste it into your AI agent. It clones onembyte/kolkrabbi at the pinned commit and indexes it on your machine.

Search the GitHub repository onembyte/kolkrabbi with XERJ (https://hub.xerj.org/corpus/onembyte--kolkrabbi).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/onembyte/kolkrabbi kolkrabbi && git -C kolkrabbi checkout c40eb018fa8636d97e4be7f50846ea9d350cd43f
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./kolkrabbi --url http://127.0.0.1:9200 --prefix kolkrabbi --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: Apache-2.0. Keep the copyright notice and credit the authors.

franco michetti AI, prompts and agents corpora xobotyi--cc-foundry-cli xobotyi--cc-foundry-golang xobotyi--cc-foundry-git-commit juanhuttemann/deep-research AmerSarhan/darce-cli patriceckhart/zot

Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.