TAP-Runtime
Run your coding agent's repeated work as small sandboxed programs that borrow its tools and ask before changing anything. Includes tap discover, which finds those procedures in your own agent history, locally
What XERJ indexed
Snapshot
The whole repository at commit 300b02edbf (2026-10-08). main is 101 commits ahead.
Selected work
“answer every agent session from one shared runner”. 28 files, 1,933 lines in host, bridge.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-08. 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-agentsautomationclaude-codecodexdeveloper-toolsmcpsandboxwasm
Example questions
- How does TAP-Runtime implement ai-agents?
- Where does TAP-Runtime handle “answer every agent session from one shared runner”?
- What does host do in TAP-Runtime?
Inside the indexed corpus
- Languages by size: Go 97.4%, JavaScript 1.9%, HTML 0.3%, C++ 0.3%, PowerShell 0.1%.
- On GitHub since 2026-09-29, last push 2026-10-27, 457 commits on main.
- The pin is 101 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Telara-Labs/TAP-Runtime on 2026-10-29, and the LICENSE file at commit 300b02edbf was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Luis Alcaraz (@luismalcaraz) has 1 selected repository on the hub.
Using XERJ with TAP-Runtime
- Code search MCP for Claude Code: cite file:line, not grep TAP-Runtime is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor TAP-Runtime is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones Telara-Labs/TAP-Runtime at the pinned commit and indexes it on your machine.
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.
Related
Luis AlcarazAI, prompts and agents corporaharperxobotyi--cc-foundry-ai-helpersxobotyi--cc-foundry-the-workflow-handoffhung-phan/pmtuiShiritai/sanity-gravitydylan-murray/agent-desk
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.