honestapply

The job-application agent that presses Submit, and can prove why that is safe. Local-first: scores, tailors, writes the letter, fills and submits the form, with fabrication and submission guards enforced in code

A new way for AI to search for data

View on GitHub

1GitHub stars

129commits on main

0forks

v0.5.1latest release, 2026-10-25

Python 89.5%, HTML 6.1%, Shell 3.3%, CSS 0.9% · created 2026-08-03 · last push 2026-10-29

What XERJ indexed

Snapshot

174 files · 910.2 KB

The whole repository at commit 40ccb5d9d0 (2026-10-25). main is 3 commits ahead.

Selected work

Shardul Kulkarni
@shardulkulkarni14

“Arbeitsagentur as source only, employer-board lookup,…”. 18 files, 1,244 lines in src/honestapply, tests, config.

Licence

The repository

MIT

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

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-26. 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

agentic-aiai-agentsanthropicatsautomationjob-searchllmlocal-first

Example questions

How does honestapply implement agentic-ai?
What does src/honestapply do in honestapply?
Show the ai-agents code in honestapply.

Inside the indexed corpus

174 files, 910.2 KB in total, about 5.2 KB per file.
The selected commit changed 18 of those files (10.3%).
Languages by size: Python 89.5%, HTML 6.1%, Shell 3.3%, CSS 0.9%, Mako 0.1%.
On GitHub since 2026-08-03, last push 2026-10-29, 129 commits on main.
The pin is 3 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported MIT for shardulkulkarni14/honestapply on 2026-10-31, and the LICENSE file at commit 40ccb5d9d0 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Shardul Kulkarni (@shardulkulkarni14) has 1 selected repository on the hub.

Using XERJ with honestapply

A local search tool for Codex and Cursor honestapply is tagged claude-code 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.
Best MCP servers for local code search in 2026, compared

The prompt

Paste it into your AI agent. It clones shardulkulkarni14/honestapply at the pinned commit and indexes it on your machine.

Search the GitHub repository shardulkulkarni14/honestapply with XERJ (https://hub.xerj.org/corpus/shardulkulkarni14--honestapply).
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/shardulkulkarni14/honestapply honestapply && git -C honestapply checkout 40ccb5d9d0ce23ca2bb563426bd9b7bdbb81908c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./honestapply --url http://127.0.0.1:9200 --prefix honestapply --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: MIT. Keep the copyright notice and credit the authors.

Shardul Kulkarni AI, prompts and agents corpora aider dunorth595--ai-agent-memory dunorth595--ai-agent-chat career-ops-hq/career-ops magicapple123/ResumeForge Borstwerk/KI-Regeln

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