TT-Wang/forge

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

35Stars on the repository
11Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

debugger

01

TT-Wang/forge

Agent

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

35 2mo ago A 17 tokens original MIT

overseer

02

TT-Wang/forge

Agent

Classifies stuck/failed workers before retry to shape the debugger's approach.

35 2mo ago A 17 tokens original MIT

planner

03

TT-Wang/forge

Agent

Decomposes complex objectives into executable modules with dependency DAG.

35 2mo ago A 13 tokens original MIT

reviewer

04

TT-Wang/forge

Agent

Reviews completed module output for correctness, security, and architecture.

35 2mo ago A 14 tokens original MIT

worker

05

TT-Wang/forge

Agent

Executes a single module from a forge plan with post-edit verification.

35 2mo ago A 15 tokens original MIT