MikeTrendsTrends right now
AI: reposAPI

search

coding agents

Trends

  1. 1
    Caveman-style tool claims 65% token savings for coding agents●JuliusBrussee/caveman⬢github2717 min ago

    Developer JuliusBrussee released Caveman, an open-source Go tool on GitHub that acts as a skill and proxy for coding agents like AI assistants. It rewrites the agent's output into terse, 'caveman-style' language, cutting token usage by a claimed 65% and lowering API costs. The humorous framing — 'why use many token when few token do trick' — has helped it spread quickly among developers.

  2. 2
    Open-source model routing launched for coding agents●Show HN: Open-source model routing for coding agents at Astra-level performanceYhnEnvironmentOceans1104 min ago

    A developer has released an open-source model routing tool for coding agents, claiming performance on par with Astra. The launch invites developers to route coding tasks across models to reach top-tier results without proprietary systems, and it is drawing attention from the Hacker News community as a practical alternative for agent builders.

  3. 3
    Superpowers framework for AI coding agents gains attention●obra/superpowers⬢github5617 min ago

    Developer Jesse Vincent, known online as obra, has released Superpowers, an open-source framework that provides agentic skills and a software development methodology for AI coding agents. Written in Shell, the project describes itself as a practical way to structure how AI agents plan and execute programming work. It is currently trending among developers following the rapid growth of agentic coding tools.

  4. 4
    Ponytail tool pushes AI agents to write less code●DietrichGebert/ponytail⬢github1.4K7 min ago

    Developer Dietrich Gebert has released Ponytail, an open-source JavaScript tool described as making AI coding agents think like the laziest senior developer in the room. Its guiding principle is that the best code is the code never written, pushing agents toward minimal solutions, reuse of existing code and avoiding unnecessary complexity.

  5. 5
    Matt Pocock releases engineering agent skills repository●mattpocock/skills⬢github9557 min ago

    Developer and TypeScript educator Matt Pocock has published a repository called 'skills', a collection of agent configurations described as 'Skills for Real Engineers', drawn directly from his personal .agents directory. The project is written mostly in Shell and is climbing GitHub's trending ranks quickly, drawing attention from developers interested in practical, battle-tested setups for AI coding agents.

  6. 6
    Context-mode tool promises 98% cut in AI agent token use●mksglu/context-mode⬢github2767 min ago

    A new open-source project called context-mode, written in TypeScript and published on GitHub by developer mksglu, targets context window optimization for AI coding agents. It claims to sandbox tool output for a 98% reduction in tokens, persist session memory, and enforce routing across 17 platforms using MCP and hooks. Developers are taking an early look as agent tooling costs draw scrutiny.

  7. 7
    Marketing skills toolkit released for Claude Code AI agents●coreyhaines31/marketingskills⬢github1397 min ago

    A developer has released an open-source collection of marketing skills for Claude Code and other AI agents. The toolkit covers conversion rate optimisation, copywriting, SEO, analytics and growth engineering, letting AI assistants carry out marketing tasks directly. Developers are sharing the repository as interest grows in extending coding agents into business functions beyond software development.

  8. 8
    CodeGraph tool for AI coding assistants gains attention●colbymchenry/codegraph⬢github2417 min ago

    Developer Colby McHenry released CodeGraph, an open-source tool that builds a pre-indexed knowledge graph of a codebase and automatically syncs it whenever the code changes. It works with AI coding assistants including Claude Code, Codex, Gemini CLI, Cursor, OpenCode, AntiGravity, Kiro, GitHub Copilot and Hermes Agent, running entirely locally. The promise is that assistants get better context with fewer tokens and fewer tool calls, a pain point for developers using AI on large codebases.

  9. 9
    The Four Horsemen of Agentic Coding●Yhn778 min ago

    A new essay examines the leading tools and approaches in agentic coding, where AI agents autonomously write and manage code. It lays out four dominant players or paradigms shaping this fast-moving field and weighs their strengths and drawbacks. Developer interest in AI-driven coding workflows remains intense, and pieces that compare the main contenders are drawing close attention.

  10. 10
    Ask HN: Is anyone producing good code with coding agents?●Ask HN: Is anybody producing good code with coding agents?YhnScienceBiology816 min ago

    A question posed on Hacker News asks whether developers are actually getting good, production-quality code out of AI coding agents. The discussion invites firsthand accounts from programmers on whether tools like autonomous coding assistants deliver real value or mostly need heavy review and rework.

Repos