Declarative, verifiable DAG orchestration for Claude Code subagents — fan-out, gates, loops, tournaments, approvals, resumable runs, and saveable commands, with intermediate transcripts kept out of your context.
DAG-based lossless context management for Claude Code. Every message from every session is persisted in a SQLite vault with FTS5 search. Summaries form a directed acyclic graph - nothing is ever lost.
★not rated 15 5mo agoA
tokens not measured
originalMIT
Local-first LLM branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, regression-test LLM calls as a DAG, and archive context as encrypted, restorable capsules. Teaches Claude when and how to drive ForkMind.
★not rated 3 1mo agoA
tokens not measured
originalMIT
Runs coding work as an explicit execution graph (DAG) instead of a natural-language conversation. Deterministic work is executed by the server with zero LLM calls, the points where a human steps in are declared in the graph, and run state is owned by the server rather than the conversation.
★not rated 0 2mo agoA
tokens not measured
originalMIT