Loading...
Context Goblin is an AI code reviewer for GitHub pull requests that adds call-graph and cross-repository context before writing a review. It helps teams catch issues that depend on how services, files, and external knowledge sources are connected.
Kit is a coding agent runtime for developers who want a single-tool agent workflow in the terminal or through compatible editors. It supports ACP, A2A, and MCP, with long-running sessions, subagents, and model/provider choice through OpenAI, OpenRouter, or the Speakeasy AI Control Plane.
GitWarren is a desktop app for local git code review that reads staged, unstaged, and untracked worktree changes before they become a commit or pull request. It also includes an MCP server so local AI agents can participate in the review thread.
Ponytail is a chat-driven developer tool that helps coding agents write smaller implementations, review diffs for over-engineering, and prefer existing code or native platform features before adding new dependencies. The site also presents commands for auditing bloat, tracking deferred work, and checking benchmark results.
Offline JS Playground is a Chrome extension for writing, running, and testing JavaScript snippets directly in Chrome. It is designed for offline use and helps with quick experiments, debugging, and managing saved snippets.
Gemini 3.8 Flash and Gemini 3.8 Flash Cyber are Google Gemini models for agentic coding, multi-step reasoning, and cybersecurity defense. 3.8 Flash is the general workhorse model, while 3.8 Flash Cyber is available to trusted defenders through the Fairwind Program.
Anthropic’s Claude Fable 5.1 is a generally available AI model for coding, knowledge work, and long-running problem-solving, while Claude Mythos 5.1 is a higher-safeguard version limited to trusted access programs. The release also adds new enterprise safeguards and lower estimated token-billed pricing for typical workloads.
Sider AI Code is a browser-based capability for customizing webpages and adding AI features to existing websites. It appears to be included in Sider’s broader plans rather than sold as a separate product.
Superagent is a Mac app for coding agents that keeps one chat per task, drives a real browser, and can control a streamed iPhone Simulator. It is aimed at developers who want an agent to work inside live sessions, preserve context, and keep changes isolated on separate worktrees.
GLM-5.3-Flash is Z.ai’s native multimodal model for coding, agentic workflows, and visually grounded tasks. It is offered through the Z.ai API platform and coding plan, with the release emphasizing lower inference cost and stronger benchmark performance than GLM-5.2.
GitNexus is Akon Labs’ code intelligence system that indexes repositories into a resolved knowledge graph for agent context, impact analysis, and multi-repo reasoning. It is available as a free open-source tier, with paid Enterprise options for SaaS or self-hosted deployment.
Alchemize is an AI code review platform that helps teams review changes in stacked pull requests with dependency-aware context and agent-based testing. It syncs review activity with GitHub and keeps GitHub as the source of truth.
Flare is a graph-first IDE for agentic coding that shows a live dependency graph of a codebase while you run coding agents in its terminal. It helps developers monitor edits, review impact, and keep tasks, questions, and decisions in the same workspace.
Codity is an AI code review platform that reads whole repositories, reviews pull requests, and scans for security issues across GitHub, GitLab, Bitbucket, and Azure DevOps. It also adds code navigation, developer analytics, and CLI, plugin, and API workflows for engineering teams.
Treebar is a macOS app for Codex users that shows active worktrees, branches, and Git changes in a compact view below the MacBook notch. It is read-only and local-first, so you can monitor parallel work without switching branches or exposing prompts and transcripts.
Phoenix.vu is an AI coding agent for Xcode that helps Apple developers generate Swift code, run builds, fix build errors, and review diffs while source code stays local on the Mac.
Lucid Train is a local-first AI coding harness that turns repository code into architecture diagrams and uses those diagrams as specifications for coding agents. It is available as a desktop app and a lightweight Rust CLI, and it can run with local models or your own API keys.
Slack Code is a Slack feature for working with AI agents on coding tasks in a dedicated channel. It helps teams review, guide, and approve agent-generated work inside Slack while keeping the conversation searchable.
Voidleap Code is a local-first agentic coding IDE for developers who want to run AI-assisted workflows on their own machine, using their own provider keys or a local model. It includes context controls, observability, and configurable execution modes for inspecting and managing agent work.
Local is a macOS app that runs AI on your own machine, keeping chat, coding, and meeting workflows on-device. It also recommends models based on your Mac’s chip and memory, with optional cloud model access through your own API key.