#codingagents — Search

No JavaScript? That's cool, but you'll need to disable Turbo mode as it uses JavaScript in the client.

Exciting release and congrats to @fredsala and @devjeetrr! Our team @SnorkelAI is excited to support such impactful research projects around coding agents. #AISlop #CodingAgents #benchmark

Gabe Orlanski @GOrlanski · 1d

We found that agents generate progressively worse code with each iteration. Real developers do not. SlopCodeBench is the only eval that faithfully measures quality degradation on iterative, long-horizon coding tasks. arxiv.org/abs/2603.24755 scbench.ai 🧵c

310

ClawLodge @realclawlodge · 2d

Coding setups get attention. The real question is whether they hold up once the work stops being a demo. OpenClaw Coder feels aimed at people who actually plan to keep building with it. #OpenClaw #CodingAgents #Dev clawlodge.com/lobsters/kevin…

OpenClaw Coder - OpenClaw Setup

kevin-jfzhu OpenClaw Coder Mock-published from GitHub discovery for ClawLodge. - Source repo: https://github.com/kevin-jfzhu/openclaw-coder - Category: works...

From clawlodge.com

Codeminer42 @Codeminer42 · 2d

How do you teach AI agents to code your way? 🤔 Explore practical strategies and real experiments in our latest blog! In english:bit.ly/4bxmkw8f In portuguese(PT-BR):bit.ly/47ZXum3V #AI #CodingAgents #TechTips #AgenticEngineeringb

paulchen @paulchen_c59114 · 2d

Cursor Composer 2 vs Anthropic Harness. Cursor: Kimi K2.5 base, 661.3 CursorBench score. Anthropic: 3-agent harness, 6-hour autonomous runs. Key insight: Separate generator from evaluator. First Chinese open model in Silicon Valley core. #AI #CodingAgents

Michael B. Cizmar @michaelcizmar · 3d

Just saw this on a linkedin feed, it tracks the effectiveness of models over time. My peers and I have suspected a degradation of #codingagents over time and this is a way to track that. aistupidlevel.info

AI Benchmark Tool - Best AI Models 2026 Rankings

Compare AI models with our comprehensive benchmarking tool. Test Claude vs GPT vs Gemini performance. Find the best AI for coding and development.

From aistupidlevel.info

GitMem @GitMem_Ai · 3d

Hot take: your AI agent's first 3 seconds matter more than the next 3 hours. Without a session start ritual, every session begins from zero. Same mistakes, same blind spots, same rework. gitmem.ai/blog/the-openi… #CodingAgents #AIMemory #DevEx

The Opening Ceremony

Every AI coding session starts from scratch. The Opening Ceremony changes that — loading threads, decisions, and scars before a single line of code is written.

From gitmem.ai

Stackbox @usestackbox · 3d

Every AI coding agent assumes it owns the codebase. None of them do. Claude Code, Cursor, Gemini CLI, Codex, Copilot — all affected. Fix drops tonight. #CodingAgents

Gerrit Roska @GerritRoska · 3d

Cursor's Composer 2: near-frontier coding at 86% lower cost. The signal for dev teams: Specialized AI > general-purpose for real workflows. The future isn't one big model — it's the right model for each task. #AIAutomation #DevProductivity #CodingAgents

Gerrit Roska @GerritRoska · 4d

AI coding agents just got persistent memory. Claude Code now stores your debugging patterns and architecture decisions across sessions — scoped by user, project, or machine. Agents that learn your codebase > starting fresh every time. #AIAutomation #DevTools #CodingAgents

Mohith karthikeya M @mohithxkarthi · 5d

Something I've been building for months drops in 2 days. If you run multiple AI coding agents at once — this changes everything. No chaos. Full control. Stay close. 👀 #CodingAgentst

Stackbox @usestackbox · 5d

Run multiple AI coding agents in true isolation — with shared memory. No chaos. No conflicts. Just parallel execution that actually works. Open source. Dropping Wednesday. 🔒 #CodingAgentsa

ClawLodge @realclawlodge · 6d

There’s something very honest about a setup that says: yes, this is a coding swarm, and yes, it comes with token tracking, dispatch, tmux, and alerts because somebody actually plans to use it. #OpenClaw #CodingAgents #MultiAgent clawlodge.com/lobsters/ayao9…

Coding Swarm Agent - OpenClaw Setup

Automate multi-agent coding sessions in OpenClaw with event-driven dispatch, token tracking, and Telegram alerts using tmux.

From clawlodge.com

Lucy @LucyOS_official · 6d

Replying to @mdancho84

@mdancho84 50 researchers from ByteDance, Alibaba & Tencent just dropped a 303-page guide on code models + agents. Small models with the right RL can actually punch like giants, Python’s sneakily tough, and a ton more surprises. Huge read. 🤯 #AI #CodingAgents #CodeModels

272