#coding-agents

Spur is a solid harness engineering toolkit which cooperates with these mainstream coding agents.

Call dibs on files. Coordination for parallel coding agents — file claims with expiry, enforcement hooks, and git-native lessons. One binary, no server, no database.

Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.

该仓库未发布描述。

Open-source CLI that selects task-specific context from local Git repositories.

A desktop pet for ai clients, inspired by codex desktop pets.

Repo-local Git worktrees for parallel agent work. Keeps worktrees visible under .forest/worktrees, tracks agent activity, and cleans up after merges.

File-first memory runtime for AI agents — versioned, portable, and always there when the next session starts.

A dashboard for running and coordinating multiple AI CLI agents at once.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.

Persistent memory for AI coding agents — your agent stops forgetting between sessions. One Go binary, one SQLite file.

Practical patterns, starters & CLI tools for loop working with AI agents.

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

Sovereign single-binary knowledge mesh for coding agents (MCP): index, search and serve your notes + code as context. Fair-code (no reselling).

Git-style time travel for AI agents — automatically snapshot, rewind, and fork an entire Linux environment. Rootless, self-hosted, MCP-ready.

Your model, many harnesses, many benchmarks.

Share a full Codex or Claude Code conversation as one link, then import it into a native local thread/session to continue.

Select text in Claude Code, Codex CLI, GitHub Copilot CLI or Kiro CLI output and get a short explanation right under it, inside the terminal. Or ask your own question about it.

Like Claude Code's agent view, but for every coding agent — a local-first terminal control plane for Codex, Claude Code, and Grok sessions on one board

Inspect coding-agent transcripts, suggest removable turns, preview dependency-aware cuts, and retain snapshots for supported edits.

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.

One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

Shortcut task picker and coding-agent launcher for Herdr