Category: tech > ai > agents
87 insights in this category - page 3 of 5. View all insights
Clicky - Open-Source AI Screen Guide That Shows You Where to Click
Clicky is an open-source tool that adds a guided cursor overlay to AI screen-sharing, physically showing users where to click rather than just giving text in...
Thoughts on slowing the fuck down
Mario Zechner: coding agents compound small errors at machine speed, producing brittle codebases fast. Slow down, write architecture by hand, cap agent output.
Hermes Agent - AI Agent Framework
Hermes Agent by NousResearch is a self-hosted autonomous agent with persistent memory, multi-channel messaging, and an open skill ecosystem that compounds.
Harness Engineering: Beyond Prompt and Context Engineering
Harness engineering is the scaffolding layer that lets an AI agent run for hours or days, decompose work, self-prompt at each step, and evaluate quality.
How We Built a Virtual Filesystem for Our Assistant
Mintlify replaced sandbox containers with ChromaFs, a virtual filesystem that maps UNIX shell commands to Chroma vector queries, cutting session creation 460x.
AI state of the union: we passed the inflection point
Simon Willison on Lenny's Podcast: AI coding agents crossed an inflection point in November 2025 with Claude Opus 4.5 and GPT 5.1. Dark factories are coming.
Claude Code Unpacked
An interactive deep-dive into Claude Code's internals: the agent loop, 40+ tools, multi-agent orchestration, slash commands, mapped from the open source.
Top 3 Claude Code Browser Agents
Three CLI browser agents for Claude Code: Playwright CLI (lowest tokens), Firecrawl Interact (automation plus scraping), Vercel Agent Browser (leaner, faster).
Anatomy of the .claude/ Folder
The .claude/ folder controls Claude Code behavior through instructions, permissions, commands, skills, and subagents. Keep CLAUDE.md under 200 lines.
How Stripe deploys 1,300 AI-written PRs per week
Stripe ships 1,300 agent-authored PRs a week, enabled by a decade of cloud dev environments, docs, and CI tooling that give agents a human-like workflow.
PipesHub: Self-Hosted Workplace AI Search for Google and Slack
PipesHub is an open-source, self-hostable workplace AI platform that unifies search across Google Workspace, Microsoft 365, Slack, Jira, and Confluence.
Speculative Execution in Claude Code, Hidden but Fully Built
A developer reverse-engineered Claude Code's binary and found a built but server-gated feature: speculative execution pre-runs your next action in a sandbox.
Schedule tasks on the web - Claude Code Docs
Claude Code now supports scheduled autonomous tasks that run on a cron-like schedule in the cloud, with access to GitHub repos and MCP connectors.
Sandboxing AI agents, 100x faster
Cloudflare's Dynamic Worker Loader spins up V8 sandboxes in milliseconds, making per-request AI agent isolation 100x faster than containers.
GSD, a Meta-Prompting System That Solves Context Window Degradation
GSD solves context window degradation by breaking work into atomic plans executed in fresh subagent contexts with parallel wave execution.
Claude Code's Dream Feature, Garbage Collection for AI Memory
Claude Code's Dream feature automatically cleans memory files by resolving contradictions, merging duplicates, and removing stale information.
Everything Claude Code: 28 Agents and 125 Skills to Cut Costs
Everything Claude Code is an optimization system with 28 agents, 125 skills, and 60 commands that can cut AI coding costs by 60% or more.
CLI-Anything: Auto-Generated CLI Wrappers for Desktop Apps
CLI-Anything auto-generates CLI wrappers for desktop software like GIMP and Blender, making them controllable by AI agents like Claude Code.
NanoClaw Runs Claude in Isolated Containers for WhatsApp and Telegram
NanoClaw runs Claude Code in isolated containers connected to WhatsApp and Telegram, with only 15 source files and 3,900 lines of code.
ProofShot - Visual proof for AI-built code
ProofShot records video and screenshots while AI agents interact with browsers, packaging everything into standalone HTML proof artifacts.