| 10/11 | 8 |
A dsh plugin that provides access to frontier models like DeepSeek V4.1 Flash and Kimi K3 without login, sign-up, or API keys.
|
| 10/11 | 8 |
Agent-driven reverse-engineering workflow that analyzes app behavior and binaries, records evidence, and recreates adapted implementations for your stack and requirements.
|
| 10/10 | 8 |
Rakazo is a Grok Bot alternative that runs sandboxed, multi-bot agents across web, desktop, and mobile using a user-supplied model and isolated runtimes.
|
| 10/10 | 8 |
Directory-based manager that centralizes AI assistant rules and context and generates native configs for various AI tools.
|
| 10/11 | 7 |
Self-hosted gateway that turns REST, OpenAPI, SOAP, GraphQL, and SQL APIs into MCP tools for Claude and ChatGPT using ready connectors.
|
| 10/11 | 7 |
Kanban-first mission control that runs parallel AI coding agents using per-task git worktrees and tmux terminals to keep one workflow focused.
|
| 10/11 | 7 |
Extensible AI workspace for professional document work, combining agent-assisted edits, source-linked evidence, version history, and reviewable collaboration workflows starting with legal documents.
|
| 10/11 | 7 |
Multi-agent orchestration platform that runs lead and worker AI coding agents in Docker, coordinating tasks, integrations, and persistent memory.
|
| 10/11 | 7 |
Command-line tool automating Toss Securities web workflows, offering account, quote, portfolio, watchlist, and read-only trading commands.
|
| 10/10 | 7 |
Hive orchestrates AI agents for issue and pull request workflows in Go, using deterministic shell pipelines for governance before LLM-driven judgment and PR creation.
|
| 10/10 | 7 |
Prints token-efficient, agent-focused Go CLIs with Claude Code skills and MCP servers by extracting APIs and syncing data to SQLite.
|
| 10/10 | 7 |
Provides shared context, memory, and task coordination for AI coding agents via a single Go binary with local SQLite and hybrid keyword/semantic search.
|
| 10/10 | 7 |
Local-first desktop workspace where persistent AI agents get per-agent queues, file transfers, embedded browser control, and agent-to-agent messaging.
|
| 10/10 | 7 |
Fast, isolated local React Native environments for coding agents, with per-worktree Metro ports and simulators plus shared build caches and safe cleanup.
|
| 10/10 | 7 |
Biologically inspired memory layer for AI agents with decay, consolidation, and cross-tool portability.
|
| 10/10 | 7 |
Go-based AI agent framework with self-improving error memory, multi-provider LLM routing, script/HTTP tool extensions, and OS-native sandboxing.
|
| 10/10 | 7 |
Command-grade access layer exposing websites, desktop apps, CLIs, and system capabilities as searchable, self-repairing commands for AI agents.
|
| 10/10 | 7 |
Gnuboard7 is a modern, extensible CMS platform built with Laravel and React, featuring JSON-driven React UI and role-based permissions.
|
| 10/10 | 7 |
Local-first chat app that runs multiple AI agents with separate models, memory, and connected apps on your own machine.
|
| 10/10 | 7 |
EasyMint is a desktop Pi Coding Agent platform that guides AI through task creation, building, evaluation, and HTML or terminal workflows.
|
| 10/11 | 6 |
Persistent memory, real-time messaging, and an evolution engine for AI agents with one-command self-hosting.
|
| 10/11 | 6 |
Daintree is a macro-orchestration app for running many AI coding agent terminals in parallel across git worktrees with context injection and workflow automation.
|
| 10/11 | 6 |
Claude Code, Codex, OpenClaw, and other agents into a shared, encrypted workstation that enables cross-agent handoff, peer review, and nightly self-improvement.
|
| 10/11 | 6 |
Local file-based interoperability bus that coordinates agent conversations, threads, routing, and delivery state with crash-safe maildir-style messages.
|
| 10/11 | 6 |
Herdr-based web and PWA client that lets users access terminals, inspect agent sessions, and review files and diffs from desktop or mobile.
|
| 10/11 | 6 |
Indexes and converts local files into searchable, agent-ready text with semantic and keyword search via MCP clients.
|
| 10/10 | 6 |
Pre-push AI code review that runs scanners on changed lines and uses a separate reviewer process to validate findings and generate report artifacts.
|
| 10/10 | 6 |
Windows-first local AI-agent runtime and MCP gateway that exposes trusted capabilities through MCP for files, Git, processes, Windows automation, WSL, browser control, indexing, and observability.
|
| 10/10 | 6 |
Cross-platform AI agent platform for building, deploying, and managing intelligent conversational agents with multi-LLM support, chat and voice, training, and enterprise features.
|
| 10/10 | 6 |
Deterministic coding agent orchestrator that spawns ephemeral subagents to perform exact-match code edits and avoid context bloat.
|
| 10/10 | 6 |
Self-hosted, typed memory server that shares agent decisions and context across multiple AI agents via MCP with provenance, history, and poisoning-aware storage.
|
| 10/10 | 6 |
Instructional kit and runnable skills that enable Claude to generate token-driven, accessible components and design systems for any framework.
|
| 10/10 | 6 |
Spec-driven decision engine that governs AI workflow execution using Definition-of-Ready gates, orchestration, reviewers, and DSSE attestations.
|
| 10/10 | 6 |
Reminal streams and mirrors a machine’s real windows and full terminal into any browser with end-to-end encryption and no open ports.
|
| 10/10 | 6 |
Local-first desktop workspace that runs personal AI agents in rooms with chained leadership, local memory, file-based skills, and human-gated actions.
|
| 10/10 | 6 |
Local-first AI office agent that generates and edits PPT, Word, and Excel files by using pluggable LLM backends without storing chat logs.
|
| 10/10 | 6 |
Local-first agent platform that runs task-based role agents to plan, implement, test, and open pull requests locally on your machine.
|
| 10/11 | 5 |
TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.
|
| 10/11 | 5 |
Knowledge server exposing Markdown files with Git versioning, full-text and vector search, and an Obsidian-like web UI.
|
| 10/11 | 5 |
Terminal for running and managing 10+ parallel CLI coding agents locally.
|
| 10/10 | 5 |
On-device context engine providing retrieval-augmented memory, hooks, and an MCP server for Claude Code, OpenClaw, and Hermes agents.
|
| 10/10 | 5 |
Local tmux-first workspace that lets one AI coding agent spawn, steer, and supervise other agent CLIs via MCP with shared TUI, Web UI, and CLI control.
|
| 10/10 | 5 |
Provider-neutral AI coworker that runs durable, event-sourced agent sessions with isolated Linux sandboxes and team context to produce complete artifacts and PRs.
|
| 10/11 | 4 |
Desktop app turning task lists into AI-powered agents that triage, execute, and manage tasks locally.
|
| 10/11 | 4 |
Local evidence debugger for TypeScript AI agents that turns runs into execution trees for debugging, regression checks, and share-checked offline artifacts.
|
| 10/11 | 4 |
Persistent AI agent platform using QEMU virtual machines with a desktop, browser, memory, and permissioned tools, exposed via multiple interfaces and backed by OpenRouter models.
|
| 10/11 | 4 |
Local-first AI agent desktop client combining multi-model chat with local tool execution, MCP tool bridging, and a remote gateway for access and collaboration.
|
| 10/10 | 3 |
Terminal-native workspace that runs multiple coding tasks in parallel using isolated git worktrees and persistent agent or shell sessions.
|
| 10/10 | 2 |
Poracode is a desktop app that runs multiple AI coding agents side-by-side with unified chat, terminals, layouts, and built-in MCP orchestration.
|