Hyperagents: Self-Referential Meta-Agents (2026)
Meta FAIR: task agent and meta agent unified in a single editable program — meta layer can modify itself (recursive self-improvement); validated on code, paper review, robotics, and olympiad math; 2.1k HF likes; open source (facebookresearch/HyperAgents)
Jumblejournal
New AI ToolsEnhance Self-Awareness with Jumble Journal: Your AI-Powered Diary Companion.
Optimality of LLMs on Planning Problems (April 2026)
Google DeepMind: first systematic study of whether LLMs produce *optimal* plans (not just valid); reasoning-enhanced LLMs significantly outperform classical satisficing planners (LAMA) in complex multi-goal configurations
Rockett AI
Graphic Design ToolsRockett AI helps you generate engaging marketing content, graphics, and social media posts in seconds using AI-driven automation.
GraphRAG (2025)
Graph-structured retrieval enabling multi-hop reasoning
<div align="center"><img src="https://raw.githubusercontent.com/evilsocket/search/refs/heads/main/logo.png" height="20"/></div>
[Nerve](https://github.com/evilsocket/nerve)
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI (May 2026)
Google DeepMind: interactive workbench for open-ended mathematical research — ideation, literature search, computational exploration, theorem proving, theory building; manages uncertainty, tracks failed hypotheses, outputs native mathematical artifacts; scores 48% on FrontierMath Tier 4, a new high
Dav1dde/glad
Multi-Language Vulkan/GL/GLES/EGL/GLX/WGL Loader-Generator based on the official specs.
FLARE: Why Reasoning Fails to Plan (2026)
Diagnoses root cause of LLM agent long-horizon planning failures (stepwise reasoning induces greedy policy); FLARE (Future-aware Lookahead + Reward Estimation) lets LLaMA-8B surpass GPT-4o on planning benchmarks
Contenda
Create the content your audience wants, from content you've already made.
Tech2Transfer
AI AgentsEuropean partner for technology transfer
grok studio
New AI ToolsCollaborative AI Workspace for Docs, Code, and Games
Procedural Knowledge at Scale Improves Reasoning (April 2026)
Meta AI: RAG for reasoning — decomposes trajectories into 32M reusable subquestion-subroutine pairs; retrieves procedural "how-to" knowledge within reasoning traces; +19.2% across math/science/coding
Rethinking Generalization in Reasoning SFT (April 2026)
Challenges "SFT memorizes, RL generalizes" — reasoning SFT with long CoT does generalize cross-domain, conditional on optimization dynamics; discovers safety-reasoning tradeoff (reasoning improves but safety degrades); 152 HF likes
Gemini Prompting Best Practices
Prompting
SkillClaw: Collective Skill Evolution with Agentic Evolver (April 2026)
Cross-user trajectories continuously aggregated and refined by autonomous evolver into shared skill repository — collective skill evolution in multi-user agent ecosystems; 142 HF likes
LangMARL: Natural Language Multi-Agent Reinforcement Learning (April 2026)
Brings credit assignment and policy gradient evolution from cooperative MARL into language space — enables LLM agents to autonomously evolve coordination strategies in dynamic environments
Llama 4 Prompt Format
Prompting
AutoMCP: Convert Agents to MCP Servers
AI AgentsBuild Purpose-Built MCP Servers from Your Prompts
SaintDoresh/Crypto-Trader-MCP-ClaudeDesktop
使用 CoinGecko API 提供加密货币市场数据的 MCP 工具。
SethGammon/Citadel
Production harness: 4-tier routing, parallel worktrees, lifecycle hooks, 6 skills
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents (May 2026)
Context-ReAct paradigm with five atomic operations (Skip, Compress, Rollback, Snippet, Delete) for adaptive context management; proves expressive completeness of Compress; LongSeeker achieves 61.5% on BrowseComp and 62.5% on BrowseComp-ZH, substantially outperforming Tongyi DeepResearch and AgentFol
STM32F7 os.mbed
ARM Cortex-M7 discovery board for STM32F7 development and prototyping
Interview Question Generator
New AI ToolsCreate Custom Interview Questions Effortlessly