TokenGuard
Zero-config local proxy and circuit breaker for LLM agents. Stops runaway loops, tracks micro-costs and prevents API credit drains. 100% localhost
What XERJ indexed
Snapshot
The whole repository at commit 769830a92e (2026-10-20). main is 16 commits ahead.
Selected work

“Add zero-latency streaming and burn-rate circuit breaker”. 11 files, 1,367 lines in tokenguard, tests, proxy.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-26. 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
ai-agentai-agentsanthropicanthropic-aicircuit-breakercrewaideepseekfastapi
Example questions
- How does TokenGuard implement ai-agent?
- Where does TokenGuard handle “Add zero-latency streaming and burn-rate circuit breaker”?
- What does tokenguard do in TokenGuard?
Inside the indexed corpus
- 125 files, 3.7 MB in total, about 30.1 KB per file.
- The selected commit changed 11 of those files (8.8%).
- Languages by size: Python 76.5%, TypeScript 17%, HTML 6%, CSS 0.4%, JavaScript 0.1%.
- On GitHub since 2026-10-09, last push 2026-10-29, 22 commits on main.
- The pin is 16 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Shvirlok/TokenGuard on 2026-10-31, and the LICENSE file at commit 769830a92e was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
latentcat (@Shvirlok) has 1 selected repository on the hub.
Using XERJ with TokenGuard
- 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
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones Shvirlok/TokenGuard at the pinned commit and indexes it on your machine.
Search the GitHub repository Shvirlok/TokenGuard with XERJ (https://hub.xerj.org/corpus/shvirlok--tokenguard). 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/Shvirlok/TokenGuard TokenGuard && git -C TokenGuard checkout 769830a92e3a08d909aee3433a9c73bb548921c7 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./TokenGuard --url http://127.0.0.1:9200 --prefix tokenguard --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
latentcatAI, prompts and agents corporaagentopsaidergriptapesany86russ/ThreadSense-AIroedyrustam/sinapsaiheadroomlabs-ai/headroom
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.