A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
GitHub repository with 1,167 stars and 147 forks.
Language: Python
Topics: agentic-ai, ai-memory, artificial-intelligence, long-term-memory, mcp, mcp-server, python, sqlite, ai-identity, claude
Trending score 1.09, activity score 0.02, stars gained +13, forks gained +0.
2026-06-04: 1,167 stars and 147 forks.
Hindsight: Agent Memory That Learns
GitHub repository with 15,663 stars and 887 forks.
Trending score: 3.63; stars gained: +129; forks gained: +5.
Language: Python
Topics: agentic-ai, agents, ai-memory, memory
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
GitHub repository with 137 stars and 4 forks.
Trending score: 2.29; stars gained: +104; forks gained: +4.
Language: Python
Topics: agentic-ai, kv-cache, llm, llm-inference, long-context, quantization
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
GitHub repository with 81,919 stars and 9,433 forks.
Trending score: 2.16; stars gained: +88; forks gained: +10.
Language: Python
Topics: ai, ai-agents, context-engine, llm-apps, rag, retrieval-augmented-generation
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
GitHub repository with 774 stars and 2 forks.
Trending score: 1.88; stars gained: +100; forks gained: +0.
Language: Python
Topics: agentic-ai, benchmark, llm, proactive-agent, search, search-agent
Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI
GitHub repository with 36,349 stars and 3,943 forks.
Trending score: 1.80; stars gained: +70; forks gained: +11.
Language: Python
Topics: agent-skills, agentic-ai, agents, ai-agents, anthropic, automation
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
GitHub repository with 32,535 stars and 2,810 forks.
Trending score: 1.76; stars gained: +71; forks gained: +7.
Language: Python
Topics: agentic-ai, agents, ai, ai-agents, context-engineering, information-retrieval
The agent that grows with you
GitHub repository with 180,642 stars and 30,980 forks.
Trending score: 5.79; stars gained: +1,360; forks gained: +322.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
GitHub repository with 4,878 stars and 485 forks.
Trending score: 4.55; stars gained: +340; forks gained: +27.
Language: Python
Topics: agent-skills, self-evolving-agents
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0
GitHub repository with 13,233 stars and 1,551 forks.
Trending score: 4.53; stars gained: +301; forks gained: +38.
Language: Python
Topics: ai-agents, claude-code, cybersecurity, incident-response, mitre-attack, penetration-testing
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
GitHub repository with 4,141 stars and 516 forks.
Trending score: 4.43; stars gained: +415; forks gained: +37.
Language: Python
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
GitHub repository with 130,131 stars and 21,146 forks.
Trending score: 4.42; stars gained: +277; forks gained: +38.
Language: Python
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
GitHub repository with 23,119 stars and 1,836 forks.
Trending score: 4.24; stars gained: +250; forks gained: +17.
Language: Python
Topics: anti-detect, bot-detection, browser-automation, chromium, cloudflare, fingerprint
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration
GitHub repository with 57,840 stars and 6,610 forks.
Trending score: 4.25; stars gained: +221; forks gained: +39.
Language: TypeScript
Topics: claude-code, swarm, agentic-ai, agentic-framework, agentic-rag, agentic-workflow
Production-ready platform for agentic workflow development.
GitHub repository with 143,870 stars and 22,638 forks.
Trending score: 3.73; stars gained: +125; forks gained: +19.
Language: TypeScript
Topics: agent, agentic-ai, agentic-framework, agentic-workflow, ai, automation
Hindsight: Agent Memory That Learns
GitHub repository with 15,663 stars and 887 forks.
Trending score: 3.63; stars gained: +129; forks gained: +5.
Language: Python
Topics: agentic-ai, agents, ai-memory, memory
为 DeepSeek 网页版注入类原生工具调用、MCP/Shell 工具、长期记忆、Skill、Agent式持续执行和定时自动化任务
GitHub repository with 492 stars and 54 forks.
Trending score: 2.65; stars gained: +18; forks gained: +4.
Language: TypeScript
Topics: ai-memory, chrome-extension, deepseek, react, typescript, wxt
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
GitHub repository with 32,132 stars and 4,147 forks.
Trending score: 2.41; stars gained: +20; forks gained: -4.
Language: TypeScript
Topics: agent, agent-native, agentic-ai, agents, ai, ai-agent
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
GitHub repository with 137 stars and 4 forks.
Trending score: 2.29; stars gained: +104; forks gained: +4.
Language: Python
Topics: agentic-ai, kv-cache, llm, llm-inference, long-context, quantization