Loading…
IDE / Agent · TabbyML
Self-hosted AI coding assistant — an on-prem Copilot alternative.
Open-source, self-hosted code-completion and answer engine that teams run on their own infrastructure for full data control. Ships IDE extensions for VS Code, JetBrains, and Vim plus an in-IDE chat. The core is Apache-2.0; enterprise features (SSO, seats) live in a separately licensed 'ee/' directory.
Model support
Self-host an open code LLM or connect an OpenAI-compatible endpoint.
Where it runs
Tags
Related in IDE / Agent
Anthropic
Anthropic's official CLI / IDE / web agent. Primary author at Blokz.
Claude Code is our lead architect. It reads the spec, drafts the diff, runs the tests, and opens the PR — across CLI, IDE extensions, the desktop app, and the web. Everything on blokz.dev was built with it.
AI insight: Ships the same agent across CLI, IDE extension, desktop, and web from one codebase — and it's the tool that wrote this very directory.
Anysphere
AI-first code editor. Multi-model, tab-completion native.
Fork of VS Code with deep model integration — multi-line tab completion, agent mode, chat with codebase context. Strong for fast iteration on existing repos.
AI insight: A full VS Code fork, so existing extensions and keybindings carry over — and one subscription covers Claude, GPT, and Gemini without a key.
Augment Code
Agentic coding assistant tuned for large, multi-repo codebases.
Augment Code is an AI coding platform whose Context Engine indexes large, multi-repo codebases so its completions, chat, and agents reason across cross-file dependencies. It runs as a VS Code and JetBrains extension, a CLI, and asynchronous remote agents, and targets engineering teams working in enterprise-scale repositories.
AI insight: Bets on a cloud Context Engine that indexes entire multi-repo codebases — built for enterprise monorepos, not single-project editing.
Google's open-source Gemini AI agent, in your terminal.
An open-source command-line agent that brings Gemini into the terminal for coding, debugging, content generation, and research. Ships built-in Google Search grounding, Model Context Protocol support, and project context via a GEMINI.md file, plus a non-interactive mode for scripting and CI. Free to use by signing in with a personal Google account, with paid options through AI Studio, Vertex AI, and Gemini Code Assist.
AI insight: Apache-2.0; a personal Google account unlocks 1,000 free requests a day on Gemini 2.5 Pro with its full 1M-token context.
GitHub (Microsoft)
AI pair programmer in your editor — completions, chat, and agents.
The original in-editor AI coding assistant, offering multi-line completions, chat with codebase context, agent mode, and a cloud coding agent that opens pull requests. Runs across VS Code, JetBrains, Visual Studio, the CLI, and GitHub.com. A free tier covers light use; paid tiers add premium models and more allowance.
AI insight: All Copilot plans moved to usage-based GitHub AI Credits billing on June 1, 2026, replacing flat request quotas.
Agentic development platform built on a VS Code fork.
Google's agent-first IDE where autonomous agents plan, execute, and verify coding tasks across the editor, terminal, and browser. A Manager view orchestrates multiple agents in parallel, and agents produce Artifacts — task lists, plans, screenshots, browser recordings — so you can check their work at a glance. Launched in public preview alongside Gemini 3.
AI insight: Agent-first fork of VS Code where agents emit verifiable Artifacts — plans, screenshots, browser recordings — not just code diffs.
AWS
Spec-driven agentic IDE — turn prompts into specs, then code.
Kiro is AWS's agentic IDE that brings engineering rigor to AI coding. Instead of vibe-coding straight to a diff, it first generates durable spec artifacts — requirements, a technical design, and a task list — then implements them. Agent hooks automate routine actions on file events, and it runs on Claude models.
AI insight: AWS-built and Claude-powered, Kiro writes a requirements→design→tasks spec to disk as durable artifacts before it generates any code.
OpenAI
OpenAI's open-source coding agent for the terminal.
A lightweight, open-source coding agent that runs locally in your terminal, reading your repository, editing files, and running commands in a conversational loop you review in real time. Built in Rust for speed, it supports Model Context Protocol tools, subagents for parallel tasks, and switching between GPT models. Sign in with a ChatGPT plan (Plus, Pro, Business, Edu, or Enterprise) or use an OpenAI API key.
AI insight: An open-source Rust rewrite of OpenAI's original TypeScript CLI; authenticate with a paid ChatGPT plan or bring your own API key.
Tabnine
Privacy-first AI coding assistant you control — completions, chat, and agents.
An AI coding assistant built for enterprise control, offering completions, chat, and agentic workflows across all major IDEs. It never trains on or retains your code, and can be deployed as SaaS, in a VPC, on-premises, or fully air-gapped. Supports access to major LLMs plus bring-your-own and private models.
AI insight: Deploys fully air-gapped on-prem with zero code retention — for teams that can't send their source to any vendor cloud.
ByteDance
Free AI-native IDE with an autonomous build mode.
VS Code-based AI IDE from ByteDance whose Builder/SOLO agent plans tasks, edits across files, runs commands, and previews results. Bundles access to frontier models like Claude, GPT, Gemini, and DeepSeek without requiring your own API key, on free and paid usage tiers.
AI insight: A VS Code fork from ByteDance that bundles frontier models with no API key, though its telemetry has drawn enterprise privacy scrutiny.