AI product Open source
spec-ptc is a Python library and demo implementing speculative programmatic tool calling (sPTC) for code-based tool-use harnesses such as Recursive Language Models (RLMs) and CodeAct. While a language model streams code for a REPL call, it identifies closed tool-call statements in the partial code, queues eligible calls as futures, and runs them in a shadow REPL so submodel or tool execution overlaps with continued code generation. When the completed code executes, speculative calls return stored results while non-speculatable or missed calls run normally; tools can be registered with decorators, including controls for speculation and purity. The repository also provides an out-of-process JSON-lines daemon with turn, token-feed, resolution, and cleanup operations, plus wrappers for Claude Code, OpenCode, and Pi-mono.
1 use taken from transcripts — each links to the moment in the video.
A library for speculative programmatic tool calling that launches model calls while code is still being generated. This allows submodel calls to run during generation rather than sequentially afterward.
1 in the library.