Results for "coding-agents"

Terminal UI that runs coding-agent CLIs such as Claude Code, Codex, OpenCode, and Gemini CLI side by side, each in its own persistent tmux session, with live status, optional per-session Git worktrees, and a diff review that sends line comments back to the agent. Apache-2.0 licensed.

Persistent agent-memory system that captures session observations, summarizes them, and retrieves relevant context across coding-agent sessions. Apache-2.0 licensed.

Records a coding-agent run below the harness and replays it offline with the network off, or forks it from a checkpoint onto another model.

Native macOS app that runs Codex, Claude Code, OpenCode and other coding-agent CLIs side by side in one window, each with its own sign-in and session history. MIT licensed.

Hierarchical coding-agent orchestrator with recursive delegation, per-node Git worktrees, configurable limits, persistent SQLite state, and live terminal monitoring and steering.

Agent-auditing framework that runs adversarial and operational inspections against AI agents, producing scored JSON and Markdown reports for CLI, CI, and agent-plugin workflows. Apache-2.0 licensed.

Open-source desktop app for coordinating autonomous coding-agent teams with inter-agent messaging, Kanban task management, and code review across Claude Code, Codex, OpenCode, Cursor, Grok, GitHub Copilot, Kiro, Z.AI, MiniMax, Kimi, and 75+ LLM providers.

Desktop voice and chat assistant for Windows, macOS, and Linux with a custom wake phrase, local speech-to-text, and a workspace that runs CLI coding agents side by side in terminal panes, working with any single model provider key or local models via Ollama. Apache-2.0 licensed.

CLI for Git worktree management and workflow automation designed for parallel AI coding-agent workflows.

Fast, flexible Rust-native LLM inference engine built on Candle. Supports text, vision, audio, image generation, and embeddings with hardware-aware auto-tuning.

Local-first agentic development environment and source-control system that connects Git commits with agent sessions, tool calls, reasoning traces, and shared memory.

Runtime-evidence toolkit for agents that coordinates PyTorch Profiler and Nsight Systems captures, preserves native traces, and compares GPU-kernel and inference runs. MIT licensed.

Browser grid of live Claude Code and Codex sessions started with one `npx` command. Each cell is a real PTY with a colour-coded status, tmux-backed persistence, and a git worktree per cell. For Claude Code, needs-you is shown separately from done, read from the CLI's own hooks. MIT licensed.

Open-source database and workspace that gives AI agents structured data, durable knowledge, docs, skills, and apps through MCP, OpenAPI, CLI, and coding-agent skills; material writes can remain reviewable ChangeRequests before becoming canonical. MIT licensed.

End-to-end sandbox execution environment framework for agentic reinforcement learning training built on Gymnasium-compatible APIs.

Syntax-aware merge tool for overlapping coding-agent changes, with branch previews and Git merge-driver integration. Apache-2.0 licensed.

Skill, Claude Code plugin and install script for omp, Claude Code and Codex that makes coding agents reply tersely in a Cockney voice and make the smallest correct change, with plain-English warnings for risky actions. MIT licensed.

Local-first TUI for observing AI coding agent sessions across Claude Code, Codex CLI, Gemini CLI, Aider, Cursor exports, OpenCode, and more.