#1 Persistent memory for AI coding agents based on real-world benchmarks
Repository Index
47,133 repositories indexed
1–24 of 32 · Most stars
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
A simple screen parsing tool towards pure vision based GUI agent
Automate browser based workflows with AI
- api
- automation
- browser
- computer
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Open source AI coding agent. Designed for large projects and real world tasks.
AI that sees your screen, listens to your conversations and tells you what to do
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
- agents
- flow-based-programming
- flow-engineering
- llm-agent
LangChain for Go, the easiest way to write LLM-based programs in Go
Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.
- mesa
- agent-based-modeling
- agent-based-simulation
- simulation-framework
De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
- agent-skills
- ai-writing
- antigravity
- claude-code
Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
- accessibility
- agent-skills
- claude-skills
- core-web-vitals
DreamFactory is a secure, self-hosted enterprise data access platform that provides governed API access to any data source, connecting enterprise applications and on-prem LLMs with role-based access and identity passthrough.
- dreamfactory
- laravel
- framework
- php
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
- agent-memory
- deepseek-harness
- local-first
- persistent-memory
Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.
- agpl
- metasearch
- privacy
- rust
Describe any machine in one line. Claude builds a photoreal, physics based, interactive simulation of it in one HTML file, plus the film to post it. An open source Claude Code skill.
- agent-skills
- claude
- claude-code
- claude-skill
Free local-first AI business advisor with evidence-linked research and verifiable pilot plans.
Ark -- Archetype-based Entity Component System (ECS) for Go.
- ecs
- entity-component-system
- go
- golang
Lancer — desktop AI workspace based on pi-gui and pi
Translated护研搭子 (Huyan Dazi, "nursing research partner") | 18 open-source AI skills for nursing research, covering literature search, study design, data, statistics, writing, and charts and figures; newly added cohort study and RCT workflows, templates, and synthetic examples.
- agent-skills
- codex
- cross-sectional-study
- evidence-based-practice
TranslatedThe doctor's manual for AI agent skills — audit, score and build skills with an evidence-based standard. Skill Doctor