Codeium - Free AI Coding Assistant and Autocomplete Extension

DeepSeek Harness v0.1 is DeepSeek's first open-source agent framework, released on August 13, 2026 under the MIT license for builders who want a transparent, swappable agent runtime rather than a closed black box. The project frames agents as 'Model + Harness = Agent' and treats the harness — the orchestration layer around the model — as the real product. Within a day its GitHub repo passed 50,...

Gitar is an AI code-review agent that finds issues in pull requests and fixes what it finds, validating changes against your pipeline. Now part of Sonar, it targets engineering teams whose senior developers lose time to pull-request triage and flaky CI. Core Features Inline findings for security problems, bugs, performance issues, edge cases, and code-quality defects, each anchored at the exact...

GitHub Copilot is Microsoft's AI pair-programmer for developers who want completions, chat, and an agent inside the editor they already use. Built into VS Code, JetBrains, Vim, Neovim, and the GitHub CLI, it suggests code, explains functions, and opens pull requests from issues. Core Features Code completion: real-time suggestions and Next Edit predictions that stay unlimited on every plan, inc...

Warp Agent CLI is a standalone multi-model coding agent for developers who want Warp's agent in any terminal, not only inside the Warp app. Warp shipped the CLI in early August 2026, unbundling the agent from its block-based terminal so it can run over SSH or inside an existing tmux setup. Core Features Runs as a plain CLI in any terminal emulator, so it works over SSH and within existing shell...

DeepSeek Harness is an open-source AI coding agent environment built by DeepSeek for developers who want a configurable alternative to OpenAI Codex and Anthropic Claude Code. Released on August 13, 2026 under the MIT license, it turns the model's reasoning into real engineering actions: reading files, calling tools, writing code, and running tests. You install it with npm install -g ds-h and la...

Vercel Agent Plugins 1.0.0 is an open, vendor-neutral standard specification for packaging AI agent extensions, designed for developers who build plugins for ChatGPT, Cursor, GitHub Copilot, Kiro, VS Code and Codex without rewriting for each client. Core Features A minimal plugin.json manifest (just $schema and name) plus fixed locations for skills/ and mcp.json, so one package works across eve...

anydoc is Firecrawl's open-source document-parsing engine for RAG pipelines, launched on August 4, 2026. Firecrawl built it to replace heavier parser stacks that stall on mixed file types, and it turns messy PDFs, Word documents, slide decks, and images into clean structured Markdown in under five milliseconds per document, already powering Firecrawl's /parse endpoint. Core Features Rust-backed...

Meta Muse Code is a terminal coding agent for software engineers who run long, multi-file jobs on macOS or Linux. Meta Superintelligence Labs shipped it in public beta on 5 August 2026 alongside Muse Spark 1.2, the reasoning model it was co-trained with. It is Meta's direct answer to Anthropic's Claude Code and OpenAI's Codex. Core Features Four cooperating agent roles - Coordinator, Explorer, ...

Grok Build is xAI's open-source Rust coding agent for local-first development that runs on the Grok 4.5 model. Released under Apache 2.0 on July 15, 2026, it is a full-screen terminal tool that reads your codebase, edits files, runs shell commands, and searches the web. It targets engineers who want an agent they can audit and point at local inference instead of a cloud-only black box. See more...

Termexo is a local Windows workbench for developers who run Claude Code and Codex CLI sessions side by side and keep losing track of which one is waiting on them. It does not replace either agent: it wraps the real PTY terminals in one project-scoped window, so the CLI stays the source of truth. Core Features Grid workspace: open many Claude Code, Codex CLI, and shell terminals in one window, a...

Amazon Q Developer is AWS's generative-AI coding assistant for developers and IT pros working across the full software development lifecycle. Powered by Amazon Bedrock, it lives inside JetBrains, VS Code, Visual Studio, Eclipse, and the terminal, and is the natural pick for teams already invested in the AWS console, Slack, or Microsoft Teams. Core Features Agentic coding: autonomously implement...

Panto AI is an AI code-review and security agent for engineering teams that scans every pull request with more than 30,000 static-analysis rules across 30+ languages and posts context-aware feedback directly inside GitHub, GitLab, Bitbucket, and Azure DevOps. Instead of a separate linter, it acts as a quality gate that understands both code and the business reason behind a change. Core Features...

Cursor is an AI-first code editor built by Anysphere as a fork of VS Code. It is for software developers who want autocomplete, chat, and an agent that can plan and apply multi-file edits inside the editor they already use, rather than switching to a separate terminal tool. Core Features Tab autocomplete predicts the next edit across multiple lines and files, not just the next token, and learns...

Kiro is an agentic AI development environment from Amazon Web Services, generally available since November 2025, that organizes coding around specs rather than one-off prompts. It ships as a desktop IDE (macOS, Windows, Linux), a CLI, a web interface, and an iOS companion, and is built on Code OSS so it imports VS Code settings and extensions. Kiro is for engineering teams that need AI-generate...

Claude Code is Anthropic's agentic coding tool that lives in your terminal and edits code on your behalf. It is aimed at developers and engineering teams who want an autonomous pair programmer that can read an entire repository, plan multi-file changes, run tests, and fix its own mistakes. It runs in your local shell and links to your editor, so the agent works wherever your code lives. Core Fe...

OpenCode is a fully open-source AI coding agent that runs in your terminal, IDE, or desktop and helps you write, run, and debug code without locking you to one model vendor. Built by Anomaly and first released in 2025, it has become the most community-backed open coding agent, with roughly 160,000 GitHub stars, 900 contributors, and about 7.5 million monthly active developers as of mid-2026. If...

Replit Agent 4 is the autonomous coding agent inside Replit's browser IDE, released in early 2026 as a generational upgrade over Agent 2. It is built for non-coders and small teams who want to describe an application in plain English and get a working, deployed full-stack app — database, backend, and UI included — without opening a local editor. Core Features Conversational build: describe an a...

OpenClaw is an open-source, local-first AI agent framework created by Peter Steinberger and released on GitHub in late 2025. It is built for people who want a persistent 'digital employee' that lives on their own machine and can send and read email, manage files, run code, and automate daily computer tasks without sending data to a third-party cloud. Core Features Local-first execution: every a...

Google Antigravity is an agent-first IDE that orchestrates up to five AI agents in parallel across your editor, terminal, and a built-in browser, built for developers who want to delegate whole features instead of typing line by line. Launched in late 2025 and maturing through 2026, it treats agents as first-class workers with their own workspaces and verification loops. Core Features Up to 5 p...

Microsoft Copilot Studio is a low-code platform on the Power Platform for building your own copilots and autonomous agents. Instead of writing the whole backend, you draw conversations, connect knowledge, and define actions, then publish the agent to Microsoft Teams, Microsoft 365 Copilot Chat, websites, social channels like Facebook and WhatsApp, and even IVR voice lines. It is Microsoft's ans...