64 results
Coding tools and autonomous agents
by Anthropic·Feb 2025
Anthropic's terminal-native coding agent that reads and edits code, runs tests, and commits to GitHub; launched as a research preview with Claude 3.7 Sonnet.
by Aider-AI·Jun 2023
Open-source Python CLI that pair-programs with LLMs on a local git repo, auto-committing diff-based multi-file edits and supporting many model providers.
by Roo Code·Nov 2024
Open-source VS Code extension (Cline fork) offering multiple agent modes (architect, code, ask, orchestrator) with support for many LLM providers and MCP.
by Codeium·Nov 2024
Codeium's VS Code-based AI IDE featuring the Cascade agent for autonomous multi-file edits, terminal execution, and codebase-wide context.
by xAI·Aug 2026
An always-on AI teammate that runs on a persistent computer and works across connected apps with approval checkpoints.
by Cognition·Mar 2024
Cognition's autonomous software engineer that plans, writes, and debugs code inside a sandboxed VM with browser and shell, delivered as a cloud agent.
by Google·Jun 2025
Open-source terminal AI agent from Google that brings Gemini into developers' shells for coding, research, and task automation, with free individual access.
by Anthropic·Aug 2026
A Chrome browser agent that can read pages, navigate tabs, enter text, and complete browser tasks using the user's existing signed-in sessions and configurable approval controls.
by OpenAI·Apr 2025
OpenAI's terminal-native coding agent installable via npm, released alongside Codex cloud; uses reasoning models like o3 and GPT-5-Codex for coding tasks.
by GitHub·Jun 2021
GitHub's AI pair programmer offering inline code completions and chat in VS Code, JetBrains, and other editors, originally powered by OpenAI Codex.
by Google·May 2025
Google Labs asynchronous coding agent that clones repos into a cloud VM, executes multi-step tasks, and returns diffs and PRs while you work elsewhere.
by Helium 10·Aug 2026
A conversational agent inside Helium 10 that reasons across Amazon seller research, advertising, commerce, billing, and account data to answer questions and recommend actions.
by GitHub·Apr 2024
Task-centric AI workspace that turns a GitHub issue into a spec, plan, and multi-file edits, delivered as a reviewable pull request in the browser.
by Replit·Sep 2024
Replit's cloud AI agent that scaffolds, codes, installs dependencies, and deploys a full-stack app from a natural-language prompt inside the Replit workspace.
by Anthropic·Aug 2025
Anthropic's Claude browser extension for Chrome enabling agentic browsing inside a tab; launched as a research preview limited to 1,000 Max-plan users.
by Smartcat·Aug 2026
An orchestration agent that selects and sequences Smartcat content, translation, review, and quality-assurance coworkers while retaining user preferences and approval points.
by Anysphere·Mar 2023
VS Code fork by Anysphere with chat, tab-completion, and agent modes for multi-file edits and terminal/tool use, supporting Claude, GPT, and other models.
by Cline·Jul 2024
Open-source VS Code extension running an autonomous coding agent; edits files, executes terminal commands, and uses MCP tools with per-step approval.
by All Hands AI·Mar 2024
Open-source autonomous coding agent (formerly OpenDevin) running in a sandboxed Docker environment; edits files, runs shell/browser tools, and calls LLMs.
by Serval·Aug 2026
An AI agent in Serval that analyzes ticket history, instructions, and operating procedures to build and configure business automations.
by SST·May 2025
Open-source TUI/CLI coding agent maintained by the SST team; runs in a terminal, supports 75+ LLM providers via Models.dev, and offers session sharing.
by OpenAI·Feb 2026
OpenAI's macOS desktop coding agent app for orchestrating multiple parallel agents on long-running tasks, distinct from Codex CLI and IDE extension.
by Mistral AI·Dec 2025
Mistral's terminal-native coding CLI agent, introduced alongside Devstral 2; open-source, supports plugins, skills, hooks, and MCP servers for end-to-end code automation.
by GitHub·May 2025
Async GitHub agent assignable to issues; spins up a sandboxed Actions environment, edits code across a repo, and returns work as a draft pull request.
