Luis Alcaraz

What an agent can do with the TAP-Runtime corpus

Telara-Labs/TAP-Runtime: Run your coding agent's repeated work as small sandboxed programs that borrow its tools and ask before changing anything. Includes tap…

• Look up how TAP-Runtime implements ai-agents, automation, claude-code, with answers cited to file and line.
• Reuse a worked example: the commit “answer every agent session from one shared runner” (28 files · Go).
• Answer from TAP-Runtime's real Go source instead of memory (AI, prompts and agents).

• Where does TAP-Runtime handle “answer every agent session from one shared runner”?
• How does TAP-Runtime implement ai-agents?
• What does host do in TAP-Runtime?

Search the GitHub repository Telara-Labs/TAP-Runtime with XERJ (https://hub.xerj.org/corpus/telara-labs--tap-runtime).
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/Telara-Labs/TAP-Runtime TAP-Runtime && git -C TAP-Runtime checkout 300b02edbf2a880539b0f1a74dfd06105d805a6e
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./TAP-Runtime --url http://127.0.0.1:9200 --prefix tap-runtime --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.

corpus telara-labs--tap-runtime · AI, prompts and agents
Related corpora: xobotyi--cc-foundry-ai-helpers-skill-engineering, caldera, juandelossantos/another-agent-skills, Shiritai/sanity-gravity
AI search and retrieval with XERJ · Case study: reference coding for agents