Loading…
Build, run, and iterate on Pi agent graphs (pi-graph) — explicit-state multi-agent workflows with isolated/thread/shared context modes, schema-validated node handoffs, conditional routing, fan-out/barrier, durable checkpoints, and human approval gates. Use when the user wants to design a multi-agent workflow, set up a pi-graph, orchestrate specialized agents (researcher/writer/reviewer loops, parallel fan-out, idea tournaments, human-in-the-loop approval), define reliable structured outputs between nodes, author a graph JSON, or validate/run/resume/visualize a graph. Reach for this only when the task genuinely needs specialization, parallelism, independent review, or persistent role memory — otherwise prefer a single agent loop.
pi-graph is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. # Pi Graph `pi-graph` orchestrates multi-agent workflows as **explicit state graphs**: nodes, schema-validated handoffs, static and conditional edges, reducers. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding pi-graph to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install huang-sh/pi-graphReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
# Pi Graph `pi-graph` orchestrates multi-agent workflows as **explicit state graphs**: nodes, schema-validated handoffs, static and conditional edges, reducers, supersteps, durable