Start with the job, then find an open-source answer

Gemini CLI lets developers work with Gemini directly from a terminal to inspect repositories, generate or edit code, debug issues, and run tool-assisted workflows. It includes file, shell, web, and search tools, supports MCP extensions and non-interactive scripting, and offers Google sign-in, API key, or Vertex AI authentication. A personal Google account can use the documented free tier.

Browser Use gives an AI agent direct browser interaction for navigation, clicking, typing, and form completion. The CLI is designed for one-off browser tasks driven by an existing agent such as Claude Code or Codex, while the Python library supports repeatable automation, parallel jobs, custom tools, and product integrations with a model provider of the developer's choice.

Codex CLI provides a local command-line entry point to OpenAI's coding agent. After installing the binary or package, run `codex` to begin working from a project terminal on macOS, Linux, or Windows. The repository focuses on the CLI while directing users to separate IDE, desktop, and web experiences when those interfaces are preferable.

Playwright drives Chromium, Firefox, and WebKit through one API for end-to-end testing and general browser automation. It can be used as a test runner or library, through a CLI designed for coding agents, or through an MCP server for LLM-driven workflows. Its VS Code extension also supports test recording, debugging, locator picking, and trace inspection.

Uptime Kuma monitors HTTP, TCP, WebSocket, ping, DNS, Docker containers, and other targets while tracking availability, latency, and certificate details. It can publish multiple status pages and send notifications through email, Telegram, Discord, Slack, and many additional services. Docker is the simplest deployment path, but its data directory must use local storage because NFS is not supported.

NextChat provides a web, PWA, and desktop chat interface for GPT, Claude, Gemini, DeepSeek, and compatible self-hosted models. Users can keep prompt templates, manage long conversations, and deploy the service through Vercel or Docker. Online providers generally require their own API configuration, while browser data is stored locally on the device.

Stirling PDF brings common document jobs such as merging, splitting, signing, redacting, converting, OCR, compression, and editing into one interface. It can run as a personal desktop application, a browser-based self-hosted service, or a private API, allowing documents to be processed without sending them to an unrelated external tool. No-code workflows and REST endpoints support repeated or integrated processing, and a basic server can be started with Docker. The project follows an open-core model, so organizations should review which enterprise capabilities and license terms apply.

claude-mem captures tool-use observations, creates semantic summaries, and makes relevant project context available in later sessions. It adds layered retrieval, history search, a web viewer, and private tags for excluding sensitive content; installation must register its hooks and worker through the provided installer or plugin flow, not only install the SDK.

OpenHands Agent Canvas is a self-hosted control center for running OpenHands, Claude Code, Codex, Gemini, and other ACP-compatible coding agents from one interface. It can switch among local, Docker, virtual-machine, and cloud backends and trigger engineering workflows on schedules or webhooks. A direct host installation grants full filesystem access. The code is currently moving to the software-agent-sdk and agent-canvas repositories.

LobeHub treats agents as the units of work, allowing users to describe a role, create an agent, connect models, skills, and MCP-compatible plugins, and organize ongoing collaboration. It is designed for people who want one place to operate and review a persistent AI team rather than hand off tasks between isolated chats. The project remains under active development, and self-hosting requires a model API key.

Use Hoppscotch to send REST, GraphQL, WebSocket, and other API requests from the web app, desktop client, or CLI. Collections, environments, scripts, and response tests turn one-off calls into repeatable workflows, while data can remain in a local session, sync through the hosted service, or run on a self-hosted deployment.

Open Design connects a local-first desktop workspace to coding agents through skills, a CLI, and an MCP server. It can generate web, desktop, and mobile prototypes, live dashboards, slide decks, images, video, and motion graphics, then preview them in a sandbox and export HTML, PDF, PPTX, or MP4 files. The app supports macOS and Windows, uses bring-your-own model credentials, and can also run headlessly from a compatible agent.

Daytona lets agents create isolated compute sandboxes through SDKs, an API, or a CLI, then execute code, manage files and processes, and preserve state with snapshots. Clients are available for several languages, including Python and TypeScript. This public repository has been unmaintained since June 2026 because core development moved to a private codebase, so it receives no further fixes or support.

AFFiNE brings documents, an edgeless whiteboard, databases, knowledge management, and planning into one workspace. Rich text, notes, web embeds, linked pages, shapes, and slides can coexist on the same canvas, while local-first storage is paired with cross-platform synchronization and real-time collaboration. The Community Edition can be self-hosted, and optional AI features can turn material into reports, slides, mind maps, or plans. It suits people who want fewer boundaries between note-taking and visual thinking.

Pi Agent Harness packages a unified multi-provider LLM API, a tool-calling runtime with state management, an interactive coding CLI, and a terminal UI as composable modules. It gives developers separate extension points for models, tools, and interfaces. Pi has no built-in permission system and inherits the launching process’s filesystem, network, and credential access, so stronger boundaries require a container or sandbox.

MetaGPT organizes product managers, architects, project managers, and engineers into a coordinated multi-agent workflow. From a one-line requirement, it can produce user stories, requirements, data structures, APIs, documentation, and a code repository. It runs from the command line or as a Python library, and requires Python 3.9 through 3.11 plus Node.js and pnpm for actual use.

Unsloth combines a web interface and a code-based package for downloading, running, training, and exporting text, audio, vision, and embedding models. It also supports dataset preparation, training monitoring, local inference endpoints, and formats such as GGUF and safetensors. Availability varies by hardware: some CPU setups are limited to chat and data workflows, while training support depends on the platform and accelerator.

awesome-claude-skills curates Claude skills, resources, and tools for document work, development, data, communication, media, project collaboration, and security, with guidance for creating custom skills. It also highlights the connect-apps plugin, which uses Composio to connect Claude to more than 500 apps for actions such as email, issues, and Slack posts. That connector needs a Composio API key, and listed projects have their own setup and licenses.