codebud
A privacy-first, local coding agent that turns natural-language requests into executable plans using locally-running LLMs (Ollama + Qwen2.5-Coder). No API keys, no telemetry; by default no data leaves your machine
What XERJ indexed
Selected work
“add agent modes enforced by SafetyEngine and Executor”. 6 files, 287 lines in tests, agent.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: approach only
automationcode-generationcoding-agentdeveloper-toolsembeddingsllmlocal-aiollama
Example questions
- How does codebud implement automation?
- Where does codebud handle “add agent modes enforced by SafetyEngine and Executor”?
- What does agent do in codebud?
Inside the indexed corpus
- Languages by size: Python 98%, Makefile 1%, M4 0.7%, Shell 0.3%.
- On GitHub since 2026-02-25, last push 2026-10-29, 214 commits on main.
Licence on GitHub and in the corpus
GitHub reported GPL-3.0 for mkhellat/codebud on 2026-10-29, and the LICENSE file at commit 76aefbfa7a was reviewed as GPL-3.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Siyâvash (@mkhellat) has 1 selected repository on the hub.
Using XERJ with codebud
- A local search tool for Codex and Cursor codebud is tagged coding-agent on GitHub.
- Local code search MCP that uses fewer tokens than grep
- RAG without a vector database: one hybrid index codebud is tagged embeddings on GitHub.
- Search API or a vector database for agent memory?
The prompt
Paste it into your AI agent. It clones mkhellat/codebud at the pinned commit and indexes it on your machine.
Search the GitHub repository mkhellat/codebud with XERJ (https://hub.xerj.org/corpus/mkhellat--codebud). 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/mkhellat/codebud codebud && git -C codebud checkout 76aefbfa7a4f932359672ff2223bd52171162bf9 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./codebud --url http://127.0.0.1:9200 --prefix codebud --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: GPL-3.0. Read it for the approach only, do not copy code.
Related
SiyâvashAI, prompts and agents corporagpt-engineeraideragnoaryanjsx/Locusjicine1360-prog/autorcodeGenesi-OS/GenesiOS
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.