Recently updated open-source projects

Qwen Code is an open-source coding agent for the terminal with Auto-Memory, Auto-Skills, subagents, agent teams, and MCP. It supports interactive and headless use, an experimental shared daemon, and providers using OpenAI, Anthropic, Gemini, Qwen, or local-model-compatible APIs. The project also ships IDE, desktop, SDK, and IM integrations; Node.js 22 or newer is required for the npm installation path.

skills-best-practices is a guidance-oriented repository for creating and maintaining agent skills. Its documented workflow covers skill descriptions, example phrases, model-assisted validation, and organizing a reusable skill library while keeping context lean. The verifiable repository content centers on a SKILL.md and supporting guidance rather than a standalone desktop application.

gptme turns a terminal into an interactive or persistent agent workspace that can inspect and change local projects, run commands, and browse the web or process images when needed. It supports several hosted model providers as well as local llama.cpp models, and can be extended through plugins, skills, MCP tools, ACP editor integration, and templates for scheduled autonomous agents.

Skill Seekers uses a Python CLI and MCP server to turn documentation sites, GitHub repositories, PDFs, videos, and other sources into structured knowledge assets. It can compare code with documentation, generate example-rich SKILL.md files, and export for Claude, Gemini, OpenAI, LangChain, and multiple vector-database formats. It also supports caching, resumable jobs, and project-configuration scanning. Basic use requires Python 3.10+ and Git; AI enhancement or upload features may need provider credentials.

grok-cli connects a terminal coding agent to xAI’s Grok API, with web and X search, sub-agents, and Telegram control while the CLI keeps running. It offers an interactive terminal UI plus a headless prompt mode. A Grok API key is required, and the community project is not affiliated with or endorsed by xAI.

Android Messages Desktop wraps the Android Messages web experience in a standalone application for Windows, macOS, and Linux, avoiding the need to keep a browser tab open. It adds system notifications, macOS badges and menu-bar behavior, Windows and Linux tray support, background operation, and multilingual spell checking. The project is not affiliated with Google, and its Windows binary is unsigned; signing Windows releases remains an unfinished roadmap item.

Claude Forge turns a mostly unconfigured Claude Code installation into a coordinated development environment for planning, TDD, review, verification, security checks, documentation, and team orchestration. It bundles specialized agents, slash commands, reusable skills, rules, and event hooks so the workflows connect instead of behaving like separate plugins. On macOS and Linux the installer uses symlinks for instant Git-based updates; Windows users rerun the installer after pulling changes.

This skill separates Amazon seller intelligence into a deterministic feed stage and an editorial stage. A script collects eight configured public sources into raw JSON, then the agent writes Chinese, English, or bilingual digests with item-specific summaries; authenticated signals stay in stdout, and social publishing is never automatic.

NanoClaw hosts personal AI agents in separate Linux containers and connects them to channels such as Telegram, Discord, and WhatsApp, with per-agent workspaces, memory, and scheduled tasks. Channels and alternative model providers are added on demand, while customization is primarily code-based; setup requires Docker, Node, pnpm, and Claude Code.

Claude Code Router provides a local model gateway and desktop control panel for Claude Code, Codex, and ZCode. Users can combine providers, define conditional routes and fallbacks, rewrite requests, rotate credentials, and inspect usage or logs from one place. After adding providers and starting the service, agent tools can share the same routing layer instead of being configured separately.

Superset coordinates command-line coding agents across isolated Git worktrees, with status monitoring, notifications, a built-in diff viewer, and one-click handoff to an editor or terminal. It works with several named agents and can accept any agent that runs in a terminal. Local development currently requires Bun, Docker, and Caddy, and downloadable Windows and Linux builds are not yet available.

blind-vault is a macOS-only local secret tool that stores credentials in Keychain and exposes only pointer metadata such as names, scopes, and dates to the agent. Its CLI injects a value into a child-process environment without printing it, and scope checks can block mismatched commands. It keeps secrets out of chats, files, and ordinary tool output, but it is not an HSM and does not protect against malware running as the same user, brief process observation, or clipboard sniffing.

Claw Code contains a Rust implementation of the `claw` terminal agent harness that can be built from source and used for diagnostics, one-shot prompts, and interactive sessions with an API key. The repository presents itself as an agent-planned and maintained museum exhibit, warns that the same-named crates.io package is the wrong install, and points practical users to LazyCodex or Gajae-Code.

Set up OpenClaw, Hermes, or LangChain Deep Agents inside NVIDIA OpenShell with a reference stack that combines guided onboarding, routed inference, network policy, and sandbox lifecycle management behind one CLI. The project focuses on safer long-running agent operation and controlled egress. It is currently described as alpha, with community support provided on a best-effort basis.

Scientific Agent Skills packages 148 reusable skills and access paths to more than 100 scientific databases across biology, chemistry, medicine, drug discovery, materials science, and scientific computing. It follows the open Agent Skills standard and can be installed in Cursor, Claude Code, Codex, and other compatible agents for multi-step research workflows.

Codebuff is an open-source terminal coding assistant that coordinates specialized agents to understand a project, find the right files, make cross-codebase changes, and run tests. Its SDK can embed agents in applications, CI/CD systems, or custom workflows, with model selection available through OpenRouter. A separate ad-supported Freebuff edition removes subscriptions and credits, but its models, daily sessions, and full-access mode vary by region.

nanobot is a lightweight personal agent runtime that works through a browser UI, terminal, or chat services including Telegram, Discord, WeChat, Slack, and email. It supports tools, web access, MCP, memory, scheduled automation, model routing, a Python SDK, and an OpenAI-compatible API; installation requires Python 3.11 or newer and a configured model provider.

Warp is an agentic development environment built around the terminal. You can use its built-in coding agent or bring command-line agents such as Claude Code, Codex, and Gemini CLI. The client codebase is open source and can be built locally; most of the repository is licensed under AGPLv3, while the Warp UI crates use MIT.