Autonomous AI agents that perform tasks independently
franklinxkk
Product-side Spec-Driven Development framework — PRD, interactive prototype, DDD handoff, AI runtime governance, acceptance gates. L0-L3 tiers, replaceable domain modules. Works with Claude Code, Cursor, Codex, OpenClaw.
...moreSantanderAI
A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration
zinanga
SDK estándar para construir plugins del Motor Agéntico (manifiesto, registry, hooks).
Schema-validated extraction of neoantigen cancer-vaccine immunogenicity data from primary papers, on the Claude Agent SDK (bring-your-own-key).
...moreDavid Cramer
OpenAI Agents SDK harness adapter for vitest-evals.
Distributed Global
Super Research — multi-agent deep-research pipeline: topic → brief → 3× deep research → NotebookLM → audio/video → delivery, driven from the web app or a paired device.
...moreesg_nut
Coinbase AgentKit ActionProvider for trading Thetanuts options on Base — for autonomous backend agents that own their own wallet (CDP, viem, Privy, server wallets).
...moreplugin87
Turn Claude into a Senior Design Architect — DTCG design tokens, 50 components, WCAG 2.2 AA→AAA + i18n/RTL accessibility, enforced single-theme consistency (contrast, hardcode, Tailwind-palette, theme-ref + CI gates), any-framework code, 138 design system
...moreGitHub Actions
damn.dev — self-hosted workspace OS for human + AI agent collaboration.
sahagan
Multi-agent workflow template — อั่งเปา (Orchestrator), พายุ (Dev Lead), ใต้ฝุ่น (QA Lead), ติ่มซำ (UX/UI Designer)
rafaeldarrigo
Autonomous support pipeline for Node.js: chat, investigation, fix, and review tiers powered by Anthropic or OpenAI (via the Vercel AI SDK), with GitHub and Sentry webhooks. Bring your own Express, Drizzle, and pg-boss.
...morejyswee
tyga.run CLI — SaaS infrastructure for coding agents. Users, billing, scheduling, support, CRM. As easy as git.
Oussema Khorchani <[email protected]>
Lightweight, local-first observability and debugging for Python AI agents.
emadjumaah
Portable AI agent execution loop — brain-agnostic, zero embedded databases
jbaldwinroberts
Persistent inner state for AI agents. Mood, energy, attention, streaks, achievements — driven by on-chain, social, and environmental signals.
...moreAgentTrust Edge — the AI Agent Harness. One decorator, full trust enforcement.
SecureFinAI Lab
Lightweight Python client for the Agentic Trading Lab REST API (LLM-powered trading agents, backtests, paper trading).
Autoresearch Team
Autonomous LLM training research stack - build and ship autonomous research systems
richcanvas
Durable resource/action/field/purpose/classification authorization over VC-compatible entitlement credentials (spec 277 §10). Matching engine + resolver; VC-proof/status layer is additive.
...morerichcanvas
AP-native registry-building primitives: Smart-Agent-anchored registry entries, signed-card binding proofs, claim-slot schemas, lifecycle call builders, and event decoders for vertical registries. External registry publication/sync stays outside Ring 0.
...moreA production-grade Python framework implementing reusable multi-agent design patterns, stateful orchestration, and resilient execution harnesses for autonomous LLM systems.
...moreislandworkflow
Free local AI agent/workflow readiness checker for structure, secret hygiene, tooling, docs, verification, automation, and Markdown/JSON reports.
...moreomarkhandji-commits
Self-hosted AI agent for safe LLM workflows: approvals, receipts, budget controls, local dashboard, CLI, Ollama, and MCP.
...moreSleepShield Research
Runtime defense against temporal backdoors in tool-using agentic LLMs