AGEX
A simple tool using agent built in python with easy to add custom tools. Works with local models and cloud models via the OpenAI style API
What XERJ indexed
Selected work
“Implemented persistent chats”. 4 files, 287 lines in the project root.
Licence
The repository
Checked by a person at the pinned commit.
The XERJ corpus
The author agreed by email on 2026-10-22. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
agentsai-agentai-agent-toolsai-agentslocal-aiopen-sourceopenai-api
Example questions
- How does AGEX implement agents?
- Where does AGEX handle “Implemented persistent chats”?
- Show the ai-agent code in AGEX.
The prompt
Paste it into your AI agent. It clones noahdeangelis/AGEX at the pinned commit and indexes it on your machine.
Search the GitHub repository noahdeangelis/AGEX with XERJ (https://hub.xerj.org/corpus/noahdeangelis--agex). 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/noahdeangelis/AGEX AGEX && git -C AGEX checkout 5cf8ccfec0f42c43bcc3e6ebfa644f996ebc133a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./AGEX --url http://127.0.0.1:9200 --prefix agex --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.
Related
noahdeangelisAI, prompts and agents corporaatomic-agentsagnoanything-llmyasik/agentlanehussainn7/plip-ossomnigent-ai/omnigent
Selected work and consent: the XERJ registry.