Tag
Explore by tags
Autonomous coding agent that runs each task in its own cloud sandbox preloaded with your repo — writing features, fixing bugs, running tests, and opening PRs. Reachable from ChatGPT web, a CLI, desktop apps, and IDEs (VS Code, JetBrains, Xcode).
Showed that fine-tuning a GPT model on public GitHub code yields a capable program synthesizer, and introduced HumanEval — the docstring-to-function benchmark that still anchors code-generation evaluation. A production variant powers GitHub Copilot.
Provides a local-first Markdown knowledge graph that LLMs and humans can both read and write via the Model Context Protocol (MCP). Features two-way, editable notes, semantic search (embeddings + hybrid ranking), and optional cloud sync and team workspaces.
Unifies visual creator tools, reusable Skills, and a Codex-powered Agent to handle video translation, image/video generation, voiceovers, and editing in one local multimodal workspace. Desktop and web clients share a synchronized state machine and keep data local by default.
Provides a local model gateway and control plane for coding agents — route Claude Code, Codex, Grok CLI, ZCode and compatible clients to multiple providers through one stable local endpoint while managing routing, failover, tools, credentials, and observability.
Connects Blender to any LLM so models can inspect, create, and modify 3D scenes via a socket-based Model Context Protocol (MCP) server; supports object manipulation, materials, renders, asset import, and executing Blender Python.
Integrates named "skills" and multi-agent workflows into developer tooling so teams can turn ideas into context-preserving, auditable code changes. Provides npm/Skills CLI install paths and plugins for Claude Code and Codex, with stable and preview release lines.
Orchestrates code-running agents to hunt verifiable open problems: schedules runs, applies null tests and skeptic re-checks, and packages found objects with short checkers so anyone can reproduce or validate a claim.
Runs many shells inside one terminal and treats coding agents as first-class panes. Combines daemon-backed persistent sessions, vim-style modal control, BSP tiling, a session rail and an Inbox that surfaces approvals, questions and finished turns from LLM-based coding agents — useful when you run and manage agent workflows alongside shells.
Turns papers, repositories, or natural-language research goals into local-first executable 'quests' that automate reproducible experiments, branching, and result-to-paper workflows. Preserves experiment history, supports web/TUI/connectors, and keeps human takeover and inspection simple.
Provides 223 production-ready agent skills and plugins plus 298 stdlib Python CLI tools to add domain expertise to coding agents. Includes cross-tool conversion (11 platforms supported), personas, orchestration patterns, and a skill security auditor.
Desktop app that runs many CLI coding agents — Claude Code, Codex, Cursor, Gemini — in parallel, each in its own git worktree and branch. A built-in diff viewer, terminal, and PR tracking let you dispatch and review 10+ agents at once.