MikeTrendsTrends right now
AI: reposAPI

search

coding agents

Trends

  1. 1
    Caveman-style tool cuts AI coding token use by 65%●JuliusBrussee/caveman⬢github19310 min ago

    Developer JuliusBrussee released 'caveman', an open-source tool written in Go that makes AI coding agents consume roughly 65% fewer tokens by having them communicate in stripped-down, simplified language. The project pairs a proxy with a skill for coding agents, and its playful 'why use many token when few token do trick' pitch has helped it gain attention among developers looking to cut API costs.

  2. 2
    Superpowers framework for agentic coding gains developer attention●obra/superpowers⬢github56110 min ago

    The open-source project obra/superpowers, written in Shell, is trending as an agentic skills framework and software development methodology. It provides a structured set of skills and workflows designed to make AI coding agents more effective in real development work. Developers are circulating it as a practical approach to orchestrating agent behavior.

  3. 3
    New 'ponytail' tool makes AI agents write less code●DietrichGebert/ponytail⬢github1.4K10 min ago

    Developer DietrichGebert has released ponytail, a JavaScript tool that prompts AI coding agents to behave like 'the laziest senior dev in the room'. Its guiding principle is that the best code is code never written, pushing assistants toward minimal changes, fewer lines and restraint instead of over-engineering. It is drawing attention in developer circles as a counterweight to AI tools that generate verbose, unnecessary code.

  4. 4
    Open-source model routing launched for coding agents▼Show HN: Open-source model routing for coding agents at Astra-level performanceYhnEnvironmentOceans1086 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.

  5. 5
    Matt Pocock publishes AI agent skills for engineers●mattpocock/skills⬢github95510 min ago

    Developer and TypeScript educator Matt Pocock has released a GitHub repository called 'skills', described as 'Skills for Real Engineers, straight from my .agents directory'. The collection is aimed at helping engineers configure AI coding agents with practical, real-world skill definitions. The repository is trending on GitHub and drawing attention from developers interested in agent workflows.

  6. 6
    HeyGen open-sources HyperFrames for agent-driven video rendering●heygen-com/hyperframes⬢github58410 min ago

    HeyGen has released HyperFrames, an open-source TypeScript project on GitHub that lets software agents produce video by writing HTML, which the tool then renders into finished video. The pitch is simple: no animation timelines or editing software, just markup written by AI agents. Early attention is coming from developers following the intersection of AI agents and programmatic video generation.

  7. 7
    Context-mode tool aims to shrink AI coding agents' memory use●mksglu/context-mode⬢github27610 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, persist session memory across sessions, and enforce routing across 17 platforms using MCP and hooks. Developers tracking agent efficiency tools are picking it up as interest in managing context costs grows.

  8. 8
    New open-source toolkit teaches marketing skills to AI agents●coreyhaines31/marketingskills⬢github13910 min ago

    Developer Corey Haines released a collection of marketing skills for Claude Code and other AI agents, covering conversion rate optimisation, copywriting, SEO, analytics and growth engineering. The JavaScript project is circulating on GitHub and drawing attention from developers and marketers interested in extending what AI coding assistants can do beyond programming tasks.

  9. 9
    Corral tool kills commands launched by AI coding agents▼Show HN: Corral – Kill every command your agent startsYhnHealthFitness1931 min ago

    A developer has released Corral, an open-source tool that automatically terminates every command started by an AI coding agent, giving users a kill switch over runaway agent processes. The tool was shared on Hacker News, where it drew early engagement. It reflects growing concerns about controlling autonomous AI agents that execute shell commands on users' machines.

  10. 10
    MLC Releases TIRx, an Open Harness for Agentic GPU Programming●TIRx Harness: An Open Compiler Harness for Agentic GPU ProgrammingYhnSportBaseball925 min ago

    The MLC team has published TIRx Harness, an open-source compiler harness designed for agentic GPU programming, letting AI agents write and optimize GPU kernels through a compiler-driven workflow. The announcement is drawing attention from developers interested in LLM-driven code generation and performance engineering, with early discussion focusing on how compiler infrastructure can make agent-written GPU code more reliable and verifiable.

  11. 11
    New agent development environment ships with orchestrator for coding agents●Agent Development Environment (ADE)and orchestrator shipping with coding agentsYhnEnvironment1341 min ago

    A project called Agent Development Environment (ADE) is being discussed as a tooling layer for building and running coding agents, shipping together with an orchestrator to coordinate them. The work, presented by Cezar at cezar.run, positions ADE as an environment purpose-built for agent development rather than general software work. Commenters appear interested in whether dedicated environments will become standard infrastructure for coding agents.

Repos