Explore AI Tools & Apps

Buzz

Block, Inc. · Coding

Buzz is a free, open-source workspace from Block where people and AI agents share the same rooms. Every message, code patch, workflow step, and approval is a signed Nostr event in one log, so team chat, Git projects, and agent activity live under a single identity model. Real AI agent collaboration needs a shared room. That's the bet here. It's built for small teams who want their agents inside the project, not bolted on through webhooks.

Freesolo Flash

Freesolo · Coding

Freesolo Flash is a managed post-training service that takes a small language model from your data to a production-ready checkpoint without you touching a GPU. You point an AI coding agent at Flash, describe the task in plain language, approve one fixed quote, and get back a deployable model with weights exported to your repo. It's built for teams that want to run their own fine-tuned small model instead of paying frontier prices for every call. Think of it as fine-tuning small models without the cluster headache.

Fluree

Fluree · Coding · Leaning

Fluree is an enterprise AI data platform built on a verifiable knowledge graph database called FlureeDB. It pulls structured and unstructured sources into one governed graph, then lets AI agents, apps, and analysts query that same graph with answers that trace back to the original records. Teams use it as the semantic data layer under GraphRAG and other AI workflows, so outputs stay citable and permissions travel with the data.

OpenCode Superapp

OpenCode Superapp · Coding

OpenCode Superapp is a native, local-first AI workspace for desktop machines that turns the OpenCode coding agent into something closer to a full app. You bring your own models, whether that's a cloud provider like OpenAI or Anthropic, a self-hosted endpoint, or local AI models running entirely on your machine through the built-in Ollama engine. Projects, files, Git, terminals, search and extensions all live in one window, and extras like voice control, browser automation and computer use ship free rather than behind a paywall.

Cosyra: AI Coding Terminal

Portable Software · Coding

Cosyra: AI Coding Terminal is a mobile cloud coding terminal that hands you a persistent Ubuntu 24.04 workspace on iPhone and Android, with Claude Code, Codex CLI, OpenCode, and Gemini CLI already installed. You point the app at your own repo and your own AI keys, so an AI coding agent on phone hardware keeps working while your laptop is shut. To run Claude Code on iPhone or Android, you open the app, start a session, and let the agent go. It doesn't try to turn your phone into a full IDE. Think of it as a remote coding workspace you carry in your pocket and check in on from the couch.

Blaxel Agent Drive

Blaxel · Coding

Blaxel Agent Drive is a distributed shared filesystem for AI agents. It gives many sandboxes one shared file tree, so agents can read and write the same files concurrently instead of copying data around. Think of it as AI agent storage built for multi-agent collaboration rather than for a single machine. It's aimed at teams running agent fleets that need to hand off work and share context in real time. At the time of writing, it's in private preview, so you'll need to request access before you can use it. Ready to see how it works? It's a simple idea, done well.

AgentLoop

aiedwardyi · Coding

AgentLoop is a local orchestration daemon that turns a bounded coding goal into shipped work. Think of it as a local agent workflow you actually own. You plan once in ChatGPT or Claude, hand over the goal, and AgentLoop runs fresh Codex or Claude Code workers cycle by cycle while an independent critic enforces the standard you wrote in GUIDELINES.md. Your project files act as memory, so nothing gets lost between cycles, and you can watch every verdict, cost, and transcript on a live dashboard. It's built for unattended coding loops you can leave running and check later.

CrawlRaven

CrawlRaven · Coding · Marketing

CrawlRaven is a web-based SEO audit platform that pulls your Google Search Console and GA4 data, merges the keyword lists you export from Ahrefs or Semrush, and runs a 200-point site crawl. Instead of another dashboard, it hands back one ranked SEO action plan: what to write, what to update, and what to fix first. That join is the whole point.

PromptQL

Hasura · Coding

PromptQL is a multiplayer AI agent built by Hasura that connects to your business data and systems and answers real questions by writing code. Instead of one person chatting with a bot in isolation, teams share threads, a shared context brain, and automations that keep improving as more people correct and refine the work. It's aimed at organizations that need grounded, traceable answers rather than confident guesses.

Kastra

Kastra · Coding

Kastra is a runtime authorization layer for AI systems. It sits in the execution path of every prompt, tool call, shell command, database query, and API request an AI agent makes, then returns an allow or deny decision in under a millisecond before any real-world action runs. Instead of watching an agent after it acts, Kastra decides what it's allowed to do first, and records each decision in a tamper-evident audit trail. For teams that need AI execution control, it's the check that happens before the damage. Not ideal, right? Anyone who's let a coding agent run loose knows the feeling. It targets developers and teams running coding agents like Claude Code, Codex CLI, and Cursor, plus enterprises that need governance over autonomous workflows.

Arkor

Arkor (arkorlab) · Coding

Arkor is an agent-native TypeScript framework and managed runtime for fine-tuning open-weight models. You describe the model you want to a coding agent, review the generated training code, run the job on managed GPUs, then serve the result behind an OpenAI-compatible endpoint. It targets TypeScript and Node developers who want fine-tuning, evaluation, and serving to live in the same codebase as the product they're shipping.

Gemini 3.6 Flash Family

Google · Coding

Gemini 3.6 Flash Family is Google's low-latency, token-efficient lineup built for scaling production AI agent models. The set spans three tiers: Gemini 3.6 Flash for higher-quality coding and knowledge work with fewer tokens, Gemini 3.5 Flash-Lite for ultra-fast high-throughput jobs, and a gated Gemini 3.5 Flash Cyber for finding and patching software vulnerabilities through the CodeMender agent. Why three models? Because one size rarely fits an agent pipeline. If you're building agents that run for hours and call tools over and over, this family is aimed at cutting the cost of each completed task, not just the sticker price per token.