Shape agent capabilities into your workflow.

claudebox launches a Claude Code project through bubblewrap on Linux or sandbox-exec on macOS. It shadows most of the home directory, mounts the project parent read-only, and blocks sensitive runtime sockets by default, with opt-in SSH, GPG, and XDG access. The project explicitly says this is not a complete security boundary; Linux is stable and macOS experimental.

QQcode is a conversational command-line coding assistant that reads project context and can search, edit, and run commands through a stateful terminal. It includes slash-command and path completion, task tracking, configurable model and permission settings, and support for macOS and Linux, with Windows marked experimental.

Brood Box launches Claude Code, Codex, and other agents inside ephemeral microVMs backed by KVM or macOS Hypervisor.framework. A copy-on-write workspace snapshot keeps real files untouched until you inspect and accept the resulting diffs, while egress profiles and selective secret forwarding reduce exposure. The project is explicitly experimental.

Wit lets agents declare planned work, reserve individual functions or types, and see overlapping intents, lock intersections, and dependency conflicts before editing. A local daemon shares the state across tools, while accepted interface contracts can be enforced at commit time. Version 1 is single-machine, requires Bun, and supports TypeScript, JavaScript, and Python; most conflicts remain advisory.

AgentLint audits the context a coding agent reads, including AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions, alongside repository conditions such as documented build commands, CI, tests, and oversized files. It runs as a standalone CLI in any Git repository, with an optional Claude Code command for teams that want the checks inside their agent workflow.

Start with a rough software idea, refine it through a design conversation, and move into implementation, or point the tool at an existing project for repeated improvement cycles. It tracks experiments locally, evaluates each change before keeping or reverting it, and can run through Claude Code, Bob Shell, or OpenAI Codex.

Keen Code is a terminal coding agent for editing, debugging, planning, refactoring, and reviewing software with several model providers. Its deliberately small toolset covers file operations, search, and shell commands, while sessions, skills, and configurable thinking support longer work. Cross-turn context is kept lean through summaries focused mainly on changed files and failed commands.

RoleCraft is a zero-dependency CLI for installing agent skills from local folders, Git repositories, SSH URLs, or npm packages. It can target many compatible agents, install declared MCP servers, keep a lockfile, check updates, verify content hashes, and reinstall in CI. Every installation receives a local static security scan for prompt injection, command injection, credential harvesting, and sensitive file access, with dangerous packages blocked unless the user explicitly overrides the gate.

Agent AFK provides an Apache-licensed harness whose prompts, gates, routing, skills, traces, and provider settings are editable. It supports terminal chat, headless background runs, Telegram notifications, orchestration commands, and migration of plugins or MCP servers from Claude Code or Codex. Node 22 is required, and optional remote notifications need their own credentials.

pi-reflect compares recent conversations and reference material with a target Markdown file, then applies small edits to files such as AGENTS.md, MEMORY.md, or SOUL.md. It backs up changes, can commit them to Git, and tracks correction trends and repeated rule failures. Each run requires pi and a configured LLM API key.

smelt combines an AI coding agent, a Vim-style editor, and its own terminal renderer in a compact CLI. Lua plugins can add keymaps, commands, tools, and modes, while provider support covers subscriptions, OpenAI-compatible APIs, and local Ollama models. The project is under active refactoring, so the latest prerelease is recommended over the older stable build.

The plugin turns an idea into numbered acceptance criteria, decomposes the work into a dependency-ordered task graph, and runs tasks in parallel isolated Git worktrees with test-driven implementation. Code review and requirement-level verification gate atomic merges, while disk-backed state supports recovery after crashes or context resets. Remote pushes still require explicit user approval.

AgentDiff captures AI-assisted edits across Claude Code, Cursor, Copilot, Codex, Windsurf, OpenCode, and Gemini, signs line-level attribution with Ed25519, and stores the evidence in Git. Its blame, diff, context, and report commands show who changed what. Pushed traces can expose short prompt excerpts to repository readers, so sensitive teams may need to disable prompt capture.

ToolRAG registers tools from MCP servers, embeds their descriptions, and uses semantic retrieval to select the functions relevant to a user query. The selected definitions can be passed in an OpenAI-compatible format and executed against the corresponding servers, while LibSQL stores the tool index and embeddings. It is aimed at assistants that need access to many APIs without sending every tool definition on every request.

AGX brings tickets, repositories, agent sessions, implementation work, and pull-request review into a local CLI and dashboard with durable checkpoints for resuming later. It supports Claude, Codex, Gemini, and Ollama with human approval gates before irreversible actions; the CLI needs Node 22.16 or newer and at least one provider CLI, while anonymous telemetry is enabled by default but can be disabled.

agent-runbook lets skill authors describe multi-agent workflows in YAML and compile them into SKILL.md files with checkpoint support. Steps declare typed inputs and JSON Schema outputs, while the compiler checks references, dependency closure, and cycles before producing the artifact. Runbooks can dispatch agents, run scripts, branch, loop, execute parallel work, and resume from a checkpoint; the project notes that its API is still changing.

Puppeteer Real Browser MCP Server starts and owns a local Chrome process for an MCP client, exposing navigation, content reading, element lookup, clicks, typing, waits, and scrolling. It defaults to a visible browser, supports headless mode, proxies, custom Chrome paths, and dedicated profiles, and closes only the process it launched. The workflow requires reading page content before interaction, allows one browser session, and does not provide a real CAPTCHA solver.

AgentPack performs a local preflight before an agent edits code. Given a task, it ranks likely files, tests, rules, skills, commands, and warnings, then renders a compact context pack with reasons and receipts for what was included or skipped. It uses local analysis and reusable caches rather than cloud indexing or model calls, and its benchmark measures file-selection overlap—not guaranteed task success—so source inspection and tests still matter.