Loading...
GitBot is a local browser workspace for reusable coding bots powered by Claude Code, Codex, or OpenCode, with persistent threads and configurable permissions.
Codex Remote provisions cloud machines, installs Codex and Claude Code, configures SSH, projects, services, and MCP servers, and manages them in a desktop app.
Claude Sonnet 5.5 is Anthropic's AI model for well-scoped coding, knowledge work, document creation, spreadsheets, and computer-interface tasks. It is designed for users who need faster iteration and lower per-task costs than Claude Sonnet 5, while more complex open-ended work may be better suited to Claude Opus 5.5.
OpenScience is an open-source AI workbench for scientific research, combining literature, coding, experiments, compute, and results in one workspace. Use free models or connect
Dezycro is an operations layer for teams using AI coding agents like Claude Code and Cursor to manage context, direct work, verify builds, and record decisions.
Claude Opus 5.5 is Anthropic’s model for complex agentic coding, computer use, knowledge work, and business workflows, with faster output and lower typical costs than Opus 5.
ResumeContext is shared memory for coding-agent projects, archiving searchable sessions so teams can continue work across agents, machines, and usage limits via MCP.
Grok 4.7 is an xAI model for coding and knowledge work, available via Grok Build, Cursor, the Grok API and more, from $2 per million input tokens.
LucentraCode is a command-line tool for autonomous AI-assisted coding with model routing, custom agents, MCP support, and headless execution.
Bolt Forge is an open-model AI agent in Bolt.new for building and iterating on apps with GLM 5.3 Flash and GLM 5.3, designed for experimentation.
Edgee Token Compression V2 cuts redundant context and model output for coding agents with tool-result trimming, task-aware tools, and brevity controls.
The Forge turns plain-language ideas into deployed apps with autonomous AI agents for planning, architecture, coding, testing, and operations.
Kilo Mobile brings Kilo’s AI coding workflow to iPhone, iPad, and Android—launch Cloud Agents, control sessions, and review GitHub pull requests.
Juggler is a visual desktop and browser workbench for AI coding agents, with inspectable tool calls, branching conversations, editable context, and local or remote sessions.
SWE-2 is Cognition’s agentic coding model for planning, implementing, testing, and verifying software changes, available via Devin Desktop and CLI.
Jackalope runs Codex, Claude Code, Grok, OpenCode, Kimi Code, and Antigravity coding agents in parallel Git worktrees for focused development and review.
Cline for Desktop is a native macOS and Windows app for coding without an editor, with flexible AI models, queued instructions, and revisable sessions.
MiniCPM5-2B is a compact 2B-class causal language model for local assistants, coding agents, tool use, long-context text processing and on-device reasoning.
Catenary is a local-first desktop IDE for orchestrating AI coding agents, terminals, editors, browsers, and git worktrees on one visual canvas for parallel tasks and reviews.
CosmoDex is a gamified coding platform for students and developers with interactive courses, coding practice, 1v1 Space Battles, XP ranks, and optional AI code review.