Direktori skill

Temukan skill yang dapat digunakan kembali untuk AI agents.

Cari skill GitHub nyata berdasarkan tugas lalu periksa stars, trust, audit, kategori, dan jalur pemasangan sebelum digunakan.

Setiap rekomendasi tetap terhubung dengan repositori, audit, dan jalur pemasangannya.

Hasil pencarian: future-visions

Direktori bahasa Inggris

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

84K
Stars
87/100
Kepercayaan
Kategori: agent-frameworksAudit

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

30K
Stars
87/100
Kepercayaan
Kategori: rag-knowledgeAudit

Agent-less vulnerability scanner for Linux, FreeBSD, Container, WordPress, Programming language libraries, Network devices

12K
Stars
85/100
Kepercayaan
Kategori: securityAudit

High accuracy RAG for answering questions from scientific documents with citations

8.7K
Stars
86/100
Kepercayaan
Kategori: dataAudit

An open-source academic paper management tool.

2.2K
Stars
76/100
Kepercayaan
Kategori: robotics-iotAudit

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

2.6K
Stars
85/100
Kepercayaan
Kategori: agent-frameworksAudit

⚡ The future of programmable SIP servers.

1.7K
Stars
76/100
Kepercayaan
Kategori: devopsAudit

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

1.3K
Stars
84/100
Kepercayaan
Kategori: media-automationAudit

Record your test suite's HTTP interactions and replay them during future test runs for fast, deterministic, accurate tests.

1.2K
Stars
80/100
Kepercayaan
Kategori: testing-qaAudit

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

1.2K
Stars
85/100
Kepercayaan
Kategori: devopsAudit

Envision a future where everyone can read all the code of an educational operating system.

3.2K
Stars
75/100
Kepercayaan
Kategori: educationAudit

A Claude Code plugin that provides a universal radial-tree exploration engine with swappable presets for divergent ideation, adversarial critique, design-space exploration, and code audit.

161
Stars
76/100
Kepercayaan
Kategori: coding-agentsAudit