search
Codex
Trends
- 1
A developer has released CodeGraph, an open-source tool that builds a pre-indexed knowledge graph of a codebase and automatically syncs it as code changes. It works with popular AI coding assistants including Claude Code, Codex, Gemini, Cursor, Copilot and others, aiming to reduce token usage and tool calls while running entirely locally.
- 2Token compression CLI launched to cut Codex and Astra costs●Show HN: Token compression CLI to save Codex/Astra costs
A developer has released a command-line tool that compresses tokens to lower the costs of running AI coding agents such as Codex and Astra. The tool aims to shrink prompts before they are sent to these services, reducing API spending for heavy users. The release is being shared and discussed by the developer community as interest in cutting LLM costs keeps growing.
- 3OpenAI launches GPT-6.1 Sol with budget Astra-like performance●OpenAI launches GPT-6.1 Sol with Astra-like performance on a budget Access gets started with ChatGPT Work and Codex, but
OpenAI has launched GPT-6.1 Sol, a model said to deliver Astra-like performance at a lower cost. Early access begins through ChatGPT Work and Codex, while broader chat availability will have to wait. The rollout is drawing attention as a bid to bring high-end AI capability to budget-conscious users and developers.
- 4Four-person consultancy ran its whole workflow on markdown files AI agents read●What held up and what we had to fix after running a four-person consultancy on a plain markdown and YAML repo that Claud
A four-person consultancy reports on a year-style retrospective of running its operations from a plain markdown and YAML repository that coding agents including Claude Code, Codex and Copilot CLI read at the start of each session. The write-up details what the setup held up well and what had to be fixed, drawing attention among developers experimenting with AI agents as core parts of their workflow.
- 5OpenAI Codex pricing gives Pro users unlimited GPT-5.6 usage●Codex Pricing: Pro has unlimited 5.6 usage
OpenAI's Codex pricing page indicates that Pro subscribers get unlimited usage of GPT-5.6 within Codex, OpenAI's coding agent. The claim is drawing attention among developers comparing plans and weighing what unlimited agent usage means for coding workflows and the value of the Pro subscription.
Repos
- mvschwarz/openrig Multi-agent harness that runs Claude Code and Codex together as one system
- yetone/magpie Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
- heygen-com/hyperframes Write HTML. Render video. Built for agents.
- kaankiziltug/logo-design-skill A comprehensive logo-design skill for Claude, Gemini CLI, Codex and other AI agents: principles, process, SVG craft, tes
- magnitudedev/magnitude Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on
- paperclipai/paperclip The open-source app everyone uses to manage agents at work
- colbymchenry/codegraph Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGrav
- mksglu/context-mode Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and
- mattpocock/skills Skills for Real Engineers. Straight from my .agents directory.
- devdotfast/whiteboard open-source canvas for thoughtful software design
- ComposioHQ/awesome-claude-skills A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
- dzhng/jevgrep Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.
- zhaoxuya520/reverse-skill Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-deman
- newliver666/apk-reverse Suitable for Android APK reverse engineering analysis
- freestylefly/WeChatBridge 微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具
- kerpopule/hermes-jev-skills Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude
- LockedinLabs-AI/agent-console Local-first observability for AI coding agents. Every Claude Code and Codex session's tokens, cache, models and cos
- tursomari/machtiani Empowering users.
- wy-coliney/jev-browser-use 5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
- alexgreensh/anidoodle Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens