Token Beggar is an open-source Claude Code plugin that checks whether a cheaper model can do a job just as well before the big model takes it, sending large tasks to one cheaper worker while design decisions stay with the model you picked.
Be the first to rate Token Beggar. Your feedback helps other users decide.
Small tasks stay in the chat. A large task, such as fixing a bug in a repository you have not read yet, goes to one cheaper worker.
The chat then checks the whole diff and runs the tests, while design, root causes and the final answer stay with the model you picked.
token-beggar doctor lists what can quietly stop routing and exits 1 when something is broken.
Similar tools in the same category — compare side-by-side
Zilla is a source-available multi-protocol gateway whose MCP Gateway gives AI agents one governed en...
Radian is a coding agent shipped as one Rust binary. It starts with no runtime to boot and spends co...
SeekStorm is sub-millisecond lexical, vector and hybrid search written in Rust. It embeds as an in-p...
Guides and comparisons about code tools
Five Show HN launches for the parts around a coding agent: shared sessions, a leaner CLI, a commit review gate, cheaper routing and one governed MCP gateway.
Discover the best AI code tools for testing automation in 2026. Generate tests, find bugs, and automate QA workflows with AI-powered testing solutions.
Explore the best AI code tools for deployment automation in 2026. From CI/CD pipeline generation to infrastructure as code, streamline deployment.
Inventory, planning, collision detection and scheduled loops: recent open-source tools for running several coding agents against one repository.
Code graphs, persistent decision memory, semantic layers and artifact plumbing: recent tools giving coding agents the context they keep losing.
