neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Minerva reads agent-harness conversations and tool calls, proposes SKILL.md files, and syncs skills across Claude Code, Codex, Cursor, and other harnesses.
Developer toolsGoGitHub @abdul-hamid-achikOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Agent library operator and stack readiness CLI/MCP for ~/.agents skills, profiles, and honest intelligence-stack health.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Skill intelligence for agent harnesses. Minerva reads conversations and
tool calls from Claude Code, Codex, Cursor, OpenCode, Copilot, Gemini,
Hermes Agent, oh-my-pi (omp), and sonar — then proposes SKILL.md files and keeps the canonical
~/.agents/skills library in sync.
It is not a second agent runtime, not Cortex, and not a monitor for
companion CLIs.
Built with Go + Cobra + MCP stdio.
Override the library root with MINERVA_AGENTS_DIR. Override the home used
to find harness session files with MINERVA_HOME (tests should set both).Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Skill intelligence for agent harnesses. Minerva reads conversations and
tool calls from Claude Code, Codex, Cursor, OpenCode, Copilot, Gemini,
Hermes Agent, oh-my-pi (omp), and sonar — then proposes SKILL.md files and keeps the canonical
~/.agents/skills library in sync.
It is not a second agent runtime, not Cortex, and not a monitor for
companion CLIs.
Built with Go + Cobra + MCP stdio.
Override the library root with MINERVA_AGENTS_DIR. Override the home used
to find harness session files with MINERVA_HOME (tests should set both).Read the full README ↗