neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Leerie is a graph-engineered task driver for Claude Code. One prompt. Finished, committed, validated code. No steering mid-run, no polishing when it's done. It runs entirely on the Claude Code CLI and
Developer toolsPython · ShellGitHub @enricaiSelf-installOwner unconfirmed
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
Leerie is a graph-engineered task driver for Claude Code. One prompt. Finished, committed, validated code. No steering mid-run, no polishing when it's done. It runs entirely on the Claude Code CLI and your existing subscription — no Anthropic API key, no per-call billing. Every worker, judgment and implementer alike, runs on Sonnet 5.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Leerie is a graph-engineered task driver for Claude Code. One prompt. Finished, committed, validated code. No steering mid-run, no polishing when it's done.
It classifies the task, decomposes it into subtasks wired into a dependency graph — nodes are subtasks, edges are requires/provides — then a deterministic Python scheduler topo-sorts that graph into waves, implements each wave in parallel isolated worktrees, validates the integrated result, and merges — beginning to end, unattended.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Leerie is a graph-engineered task driver for Claude Code. One prompt. Finished, committed, validated code. No steering mid-run, no polishing when it's done.
It classifies the task, decomposes it into subtasks wired into a dependency graph — nodes are subtasks, edges are requires/provides — then a deterministic Python scheduler topo-sorts that graph into waves, implements each wave in parallel isolated worktrees, validates the integrated result, and merges — beginning to end, unattended.Read the full README ↗