#typescript #antigravity #claude #claude_code #claude_code_hooks #claude_code_plugins #claude_code_skill #codex #codex_cli #context_mode #copilot #cursor_plugin #kiro #mcp #mcp_server #mcp_tools #openclaw #opencode #pi_agent #skills #zed_extension
Context Mode is an MCP server that fixes context window overload in AI coding tools by sandboxing raw data (like 56KB snapshots or logs) outside chats—shrinking 315KB to 5.4KB (98% savings), tracking sessions in SQLite for seamless resumes after compaction, and making LLMs generate code for analysis instead of dumping data. It installs easily on 12 platforms (Claude Code, Cursor, etc.) with hooks for auto-routing. You benefit by extending sessions 6x longer, picking up tasks instantly without re-explaining, and boosting productivity on big repos or logs.
https://github.com/mksglu/context-mode
Context Mode is an MCP server that fixes context window overload in AI coding tools by sandboxing raw data (like 56KB snapshots or logs) outside chats—shrinking 315KB to 5.4KB (98% savings), tracking sessions in SQLite for seamless resumes after compaction, and making LLMs generate code for analysis instead of dumping data. It installs easily on 12 platforms (Claude Code, Cursor, etc.) with hooks for auto-routing. You benefit by extending sessions 6x longer, picking up tasks instantly without re-explaining, and boosting productivity on big repos or logs.
https://github.com/mksglu/context-mode
GitHub
GitHub - mksglu/context-mode: Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms - mksglu/context-mode
⚡3
#go #api #claude_api #deepseek #deepseek_api #docker #freeapi #go #openai_api #proxy #proxy_server #react #vercel #vercel_deployment #zeabur
DS2API turns DeepSeek web chat into APIs compatible with OpenAI, Claude, and Gemini, using Go backend and React web UI for easy management. It supports multi-account rotation, concurrency queues, tool calling, and models like deepseek-chat/reasoner with aliases (e.g., gpt-5). Deploy simply via release binaries, Docker, Vercel, or source—edit config.json with your keys/accounts and run. You benefit by accessing DeepSeek affordably through familiar SDKs, saving costs and simplifying integration for apps or testing.
https://github.com/CJackHwang/ds2api
DS2API turns DeepSeek web chat into APIs compatible with OpenAI, Claude, and Gemini, using Go backend and React web UI for easy management. It supports multi-account rotation, concurrency queues, tool calling, and models like deepseek-chat/reasoner with aliases (e.g., gpt-5). Deploy simply via release binaries, Docker, Vercel, or source—edit config.json with your keys/accounts and run. You benefit by accessing DeepSeek affordably through familiar SDKs, saving costs and simplifying integration for apps or testing.
https://github.com/CJackHwang/ds2api
GitHub
GitHub - CJackHwang/ds2api: DeepSeek-Compatible Middleware Interface: A technical exploration project in Go, focusing on high-concurrency…
DeepSeek-Compatible Middleware Interface: A technical exploration project in Go, focusing on high-concurrency protocol adaptation. It serves as a reference implementation for converting diverse web...
❤2
#go #agents #claude_code #coding
Beads (bd) is a free CLI tool for macOS, Linux, Windows, and FreeBSD that gives AI coding agents persistent, structured memory via a version-controlled Dolt SQL database with graphs for tasks, dependencies, and hierarchies. Install once with `curl` script or brew, then `bd init` in any project—no repo cloning needed. Key commands like `bd ready`, `bd create`, and `bd update` track blockers, claim tasks, and auto-detect ready work in JSON for agents. It prevents conflicts with hash IDs, compacts old tasks, and supports stealth/git-free modes. You benefit by replacing messy plans with clear, long-term task tracking that keeps AI agents focused without losing context, boosting productivity on complex projects.
https://github.com/gastownhall/beads
Beads (bd) is a free CLI tool for macOS, Linux, Windows, and FreeBSD that gives AI coding agents persistent, structured memory via a version-controlled Dolt SQL database with graphs for tasks, dependencies, and hierarchies. Install once with `curl` script or brew, then `bd init` in any project—no repo cloning needed. Key commands like `bd ready`, `bd create`, and `bd update` track blockers, claim tasks, and auto-detect ready work in JSON for agents. It prevents conflicts with hash IDs, compacts old tasks, and supports stealth/git-free modes. You benefit by replacing messy plans with clear, long-term task tracking that keeps AI agents focused without losing context, boosting productivity on complex projects.
https://github.com/gastownhall/beads
GitHub
GitHub - gastownhall/beads: Beads - A memory upgrade for your coding agent
Beads - A memory upgrade for your coding agent. Contribute to gastownhall/beads development by creating an account on GitHub.
#rust #ai #claude #cli #coding_agent #llm #mcp #openai #rust #terminal #tui
jcode is a fast, low-RAM coding agent for Linux, macOS, and Windows that boosts your skills with multi-session workflows, smart memory recall, swarm collaboration, side panels for diagrams/files, and logins for models like Claude or OpenAI. Install easily via `curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash`, then run `jcode`. It uses far less memory (27MB vs. 300MB+ for rivals) and starts in 14ms, letting you handle many agents smoothly without slowdowns or high costs—perfect for efficient, scalable coding.
https://github.com/1jehuang/jcode
jcode is a fast, low-RAM coding agent for Linux, macOS, and Windows that boosts your skills with multi-session workflows, smart memory recall, swarm collaboration, side panels for diagrams/files, and logins for models like Claude or OpenAI. Install easily via `curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash`, then run `jcode`. It uses far less memory (27MB vs. 300MB+ for rivals) and starts in 14ms, letting you handle many agents smoothly without slowdowns or high costs—perfect for efficient, scalable coding.
https://github.com/1jehuang/jcode
GitHub
GitHub - 1jehuang/jcode: Coding Agent Harness
Coding Agent Harness. Contribute to 1jehuang/jcode development by creating an account on GitHub.
#shell #agent_skills #antigravity #antigravity_ide #claude_code #cursor #skills
Agent Skills gives AI coding agents structured workflows that follow how senior engineers build software. You get 20 skills organized across six development phases—Define, Plan, Build, Verify, Review, and Ship—each with step-by-step processes, quality gates, and verification requirements. Seven slash commands activate the right skills automatically based on what you're doing. This benefits you by ensuring AI agents consistently follow production-grade practices like writing specs before code, testing thoroughly, reviewing for quality, and deploying safely. Instead of taking shortcuts, your AI assistant now enforces the same discipline that makes reliable software, whether you're using Claude, Cursor, Gemini, or other coding tools.
https://github.com/addyosmani/agent-skills
Agent Skills gives AI coding agents structured workflows that follow how senior engineers build software. You get 20 skills organized across six development phases—Define, Plan, Build, Verify, Review, and Ship—each with step-by-step processes, quality gates, and verification requirements. Seven slash commands activate the right skills automatically based on what you're doing. This benefits you by ensuring AI agents consistently follow production-grade practices like writing specs before code, testing thoroughly, reviewing for quality, and deploying safely. Instead of taking shortcuts, your AI assistant now enforces the same discipline that makes reliable software, whether you're using Claude, Cursor, Gemini, or other coding tools.
https://github.com/addyosmani/agent-skills
GitHub
GitHub - addyosmani/agent-skills: Production-grade engineering skills for AI coding agents.
Production-grade engineering skills for AI coding agents. - addyosmani/agent-skills
❤1
#javascript #ai_agents #ai_gateway #anthropic #chatgpt #claude #claude_code #cline #codex #copilot #cursor #deepseek #free_ai #gemini #gemini_cli #llm #llm_gateway #openai #openai_proxy #qwen #token_saver
# 9Router//localhost:20128/v1`. You get unlimited coding with zero cost, no downtime, and intelligent fallback routing—perfect for developers who want maximum value from AI without subscription limits or surprise bills.
https://github.com/decolua/9router
# 9Router//localhost:20128/v1`. You get unlimited coding with zero cost, no downtime, and intelligent fallback routing—perfect for developers who want maximum value from AI without subscription limits or surprise bills.
https://github.com/decolua/9router
GitHub
GitHub - decolua/9router: Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini…
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits. - decolua/9r...
❤3
#typescript #agentmemory #agents #ai #claude #claudecode #codex #copilot #cursor #genai #harness #hermes #memory #openclaw
# agentmemory `npx @agentmemory/agentmemory`.
https://github.com/rohitg00/agentmemory
# agentmemory `npx @agentmemory/agentmemory`.
https://github.com/rohitg00/agentmemory
GitHub
GitHub - rohitg00/agentmemory: #1 Persistent memory for AI coding agents based on real-world benchmarks
#1 Persistent memory for AI coding agents based on real-world benchmarks - rohitg00/agentmemory
#python #academic_pipeline #academic_writing #ai_research #claude #claude_code #literature_review #peer_review #prompt_engineering
# Academic Research Skills for Claude Code
This is a comprehensive toolkit that helps you write research papers from start to finish. Instead of AI writing your paper alone, it works as your research partner—handling the tedious work like finding sources, checking citations, and organizing arguments, while you focus on the thinking and writing that only you can do.
The system includes four main tools: Deep Research (for finding and organizing information), Academic Paper (for writing), Academic Paper Reviewer (for getting feedback), and Academic Pipeline (which coordinates everything together). You can use individual tools or run the complete pipeline. It supports multiple languages, citation formats, and paper types. The toolkit emphasizes human control at every step—you make the final decisions, and the AI flags potential problems like hallucinated references or weak arguments. Installation takes 30 seconds via plugin marketplace, and it costs roughly $4–6 to write a complete 15,000-word paper.
https://github.com/Imbad0202/academic-research-skills
# Academic Research Skills for Claude Code
This is a comprehensive toolkit that helps you write research papers from start to finish. Instead of AI writing your paper alone, it works as your research partner—handling the tedious work like finding sources, checking citations, and organizing arguments, while you focus on the thinking and writing that only you can do.
The system includes four main tools: Deep Research (for finding and organizing information), Academic Paper (for writing), Academic Paper Reviewer (for getting feedback), and Academic Pipeline (which coordinates everything together). You can use individual tools or run the complete pipeline. It supports multiple languages, citation formats, and paper types. The toolkit emphasizes human control at every step—you make the final decisions, and the AI flags potential problems like hallucinated references or weak arguments. Installation takes 30 seconds via plugin marketplace, and it costs roughly $4–6 to write a complete 15,000-word paper.
https://github.com/Imbad0202/academic-research-skills
GitHub
GitHub - Imbad0202/academic-research-skills: Academic Research Skills for Claude Code: research → write → review → revise → finalize
Academic Research Skills for Claude Code: research → write → review → revise → finalize - Imbad0202/academic-research-skills
❤2
#python #automation #claude #mcp #notebooklm #skill
This tool turns many kinds of content, like web pages, PDFs, podcasts, videos, and files, into formats like podcasts, PPTs, mind maps, quizzes, and reports with NotebookLM. It can also handle many sources automatically, including public pages, social posts, and some paywalled articles, and it supports Chinese and English well. The benefit to you is simple: you can save time, understand content faster, and reuse the same material in the format you need for study, work, or sharing.
https://github.com/joeseesun/qiaomu-anything-to-notebooklm
This tool turns many kinds of content, like web pages, PDFs, podcasts, videos, and files, into formats like podcasts, PPTs, mind maps, quizzes, and reports with NotebookLM. It can also handle many sources automatically, including public pages, social posts, and some paywalled articles, and it supports Chinese and English well. The benefit to you is simple: you can save time, understand content faster, and reuse the same material in the format you need for study, work, or sharing.
https://github.com/joeseesun/qiaomu-anything-to-notebooklm
GitHub
GitHub - joeseesun/qiaomu-anything-to-notebooklm: Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat…
Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc. - joeseesun/qiaomu-anything-...
#typescript #agent #ai #antigravity #claude_code #copilot #cursor #skills
Agent Skills is a safe, tested library of skills that adds new powers to AI coding tools like Cursor, Claude Code, and Copilot. It gives you ready-made workflows for planning, cloud help, browser testing, design-to-code, and security review. You can install or update skills with a simple command, and the tool keeps them cached for offline use. This helps you work faster, reduce mistakes, and use AI agents with more trust and control.
https://github.com/tech-leads-club/agent-skills
Agent Skills is a safe, tested library of skills that adds new powers to AI coding tools like Cursor, Claude Code, and Copilot. It gives you ready-made workflows for planning, cloud help, browser testing, design-to-code, and security review. You can install or update skills with a simple command, and the tool keeps them cached for offline use. This helps you work faster, reduce mistakes, and use AI agents with more trust and control.
https://github.com/tech-leads-club/agent-skills
GitHub
GitHub - tech-leads-club/agent-skills: The secure, validated skill registry for professional AI coding agents. Extend Antigravity…
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence. - tech-leads-club/agent-skills