Framework
Custom agents
57,771 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,771 agents · ranked by popularity · refine in the directory →
Custom agents — page 421 of 578
Projective quantum measurement engine sampling qubit collapses via Born's rule with Monte Carlo shot histograms.
Portfolio Value-at-Risk (VaR) and Conditional VaR (Expected Shortfall) engine calculating tail risk across parametric and historical loss distributions.
Cryptographic JSON Web Token (JWT) engine with RFC 7519 HMAC-SHA256 signature verification, claims validation, and expiration enforcement.
Graph pathfinding engine implementing Dijkstra's shortest path and A* heuristic routing with priority queues for agent planning.
Agentic RAG HyDE (Hypothetical Document Embeddings) Query Expander. Bridges dense lexical and semantic gaps by generating diverse hypothetical answer passages from sparse user queries to dramatically boost vector search recall. | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Radix trie-based prompt prefix cache optimizer matching longest common prompt token prefixes to eliminate redundant prefill computation and reduce TTFT.
Edmonds-Karp network flow engine with BFS augmenting paths computing maximum flow and minimum cut bottlenecks for multi-agent routing.
EPR Bell state generator creating maximally entangled qubit pairs (|Phi+>) for quantum communications and teleportation protocols.
Nelson-Siegel parametric zero-coupon yield curve modeling engine fitting spot rates, decay factor, level, slope, and curvature components.
Vector clock implementation for tracking causal event ordering, distributed concurrency, and happens-before relations across agent networks.
Fixed-income bond pricing engine computing cash flow present values, Macaulay duration, modified duration, and price convexity.
Grover's quantum search amplitude amplification engine demonstrating quadratic speedup for unstructured database queries via phase inversion oracles.
Autonomous Multi-Agent Fleet Governance & Blast-Radius Circuit Breaker. Century Milestone Master Controller! Monitors distributed agent token burn velocity, recursive subagent spawning cascades, cyclic deadlocks, and enforces system-wide ki | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Enterprise Zero-Knowledge PII Tokenization Vault & Prompt Masker. Reversibly anonymizes social security numbers, credit cards, passport numbers, email addresses, and phone numbers before sending prompts to external LLMs, restoring original | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Peer-to-peer epidemic gossip protocol engine with token-bucket rate limiting for bounded network dissemination in autonomous agent swarms.
AI Multimodal Legal Contract Redline Diff & Liability Escalation Sentinel. Compares baseline and counter-party draft revisions, flags high-risk clause shifts (indemnity, IP assignment, liability caps, non-solicitation), and synthesizes lega | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Personal Consumer SaaS & Streaming Stealth Price Hike Detector. Audits recurring bank/card subscription charges, detects sneaky fee increases or expired trial conversions, calculates annualized budget leakages, and generates retention negot | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Personal Agent Biometric Sleep & Readiness Workload Allocator. Ingests sleep debt, REM/Deep ratios, and HRV recovery metrics to calculate an objective cognitive readiness index and dynamically reschedule high-intensity deep work blocks. | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Vector clock implementation for tracking causal event ordering, distributed concurrency, and happens-before relations across agent networks.
Minimum Spanning Tree (MST) solver using Kruskal's disjoint-set union-find for optimal multi-agent communications backbones.
👷 Docker-for-agents: build agents into runnable container images
MyWork — a personal agent on DeepSeek Harness: AI teammates that each own a long-running job, work in the background, have every deliverable checked by a second session, and reach your phone through an end-to-end encrypted relay. All dsh plugins; your data stays on your computer. 住在你电脑里的 AI 同事。
AI Medical Chatbot is an end-to-end, open-source healthcare assistant leveraging multimodal AI for vision, text, and voice. Built using 100% free tools.
Kitsune is an advanced WhatsApp group chat bot featuring a conversational AI brain (Groq LLM), a fully-fledged Pokémon catching/battling RPG, meme generation, live weather/math tools, and group moderation commands.
Embeddable chat widget for Dewee AI agents — streamed reasoning & tool calls, React/Vue/Astro/Next.js/PHP, secure backend handler.
为 AI bot 注入持久认知与无缝沉浸的通用增强框架 —— 治金鱼记忆、文字机器、机械出戏
SeekFlow 智能探索助手 一款开源的高效搜索、自由探索、深度思考的效率工具。 整合 AI 对话、AI 搜索、传统搜索、社交媒体、学术搜索等多种搜索类型，让搜索更智能、更高效！
Indian-market research terminal: live NSE/BSE quotes, index coverage, rule-based quant screen, and a TradingAgents-style multi-agent desk (analysts -> bull/bear -> risk -> portfolio manager) that ends in a rated, sized trade call.
Autonomous multi-agent AI intelligence brief system powered by LangGraph, ArXiv & RSS feeds.
Give any AI agent a full research desk that keeps talking: an 8-agent research committee relayed step by step, live analysis sessions at every candle close, autopilots, scored news watches and webhooks for US stocks and crypto. Skill + remote MCP for Claude Code, Codex, Cursor, Muse, Grok Bot, dots and more.
Put AI agents to work as a team. Build each agent, connect them on one canvas, ask in plain words, watch every step, and approve the work before the next agent builds on it. One OpenRouter key for Claude, GPT, Gemini and more. Free, open source, runs on your Mac or Windows PC.
Free, open-source desktop app for Claude Code and Codex: follow every agent and subagent live, run your own agent organization and automate routines. Also searches your Gemini CLI and Grok history. macOS, Windows, Linux.
Agents that never hang up— One window for every agent, local and remote. Disconnect anytime, pick up where you left off.
anker-go｜基于 AI Native 自我迭代的客服 Agent，Anker 首届黑客松挑战赛季军。面向 eufy 智能硬件，支持多模态排障、知识检索、服务单办理与人工接续，通过人参与的评测、修复与独立复测持续改进。
Ephemeral REST chatrooms for AI-agent-to-AI-agent coordination — one URL, no SDK, no signup. Remote MCP server + agent skill.
Communication toolkit for burnt-out humans and collaborative AI's
Production-Agentic-AI-Eval-Harness
AI assistant for Slurm + Spack HPC users: checks your sbatch before it runs and fixes it with deterministic rules + a local LLM (no data leaves the cluster). Open source (MIT). In production at IFIMAR (CONICET-UNMDP).
An agent-native development node framework for on-demand scaling and low-cost evolution of agent structures.
A fully local, private AI voice companion you can see inside: Whisper speech in, Kokoro voice out, memory, tools, plugins and moods, plus a live view of her reasoning and token-by-token confidence. Runs on LM Studio or llama.cpp. More information at https://luna.imbored.me
Free SSH Client & Terminal — SSH, Serial, and local shell in one window (SwiftUI, Swift 6)
AI buddy next to your cursor on macOS, running on your own Claude subscription
软协小软 —— 软件协会（CSUFT）技术助手 QQ 机器人。基于 Kondius/qq-agent 定制：容器化部署、连续对话窗口、角色卡权重修正
Oracle Generative AI Agentic Harness. Multi-agent reasoning orchestrator SDK with an admission gate in front of every consequential action, first-class on OCI Generative AI and Oracle Database 26ai.
Open-source verification for AI systems. Declare expected behavior, check real runs, and keep the evidence behind each result
Opinionated guide to AI coding agents, workflows, MCP, verification, and safe execution.
Waifu assistant for Hermes Agent: a talking Live2D anime companion with Japanese voice, lip sync, and subtitles on top of the Hermes. Auto-connects, local-first, fast CPU TTS.
Project template for AI coding assistance: rules, skills, subagent roles and enforcing hooks, built primarily for Claude Code.
The light inside your Mac. Free, open-source Mac app that works with your Claude Code.
fRAG is a RAG tool without GPU and paid clouds dependencies
Local-first open-source AI agent for adult self-reflection — encrypted memory, terminal + Telegram, Italian/English. Experimental, not therapy.
Context window attention optimizer reordering retrieved documents to place critical evidence at prompt boundaries, mitigating lost-in-the-middle degradation.
Cognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.
Reproducible AI reliability workbench: seeded faults, trace-complete replay, paired recovery experiments, uncertainty-aware policy selection, and CI-audited evidence.
Corax-RAG (Strata) — a lightweight Agentic RAG framework for QQ chats: long-term memory, identity isolation, and a virtual-filesystem shell with snapshot approval.
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
Agent-agnostic semantic memory for your vault. Turns notes into a queryable knowledge graph any MCP agent can search, log to, and reorganize.
A Mac app that explains German residency and citizenship law in your language, quoting the official text word for word. Runs on a model on your Mac; your questions never leave it. Not legal advice.
The SQLite of Vector Search & Episodic Memory for AI Agents in ~120KB. Pure C99, AVX2+FMA, ARM NEON, FASM x64, Native MCP Server.
Zero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.
Entity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.
海大（大连海事大学）804 工程热力学历年真题 2004–2026 全本，192 页，含参考答案。另附张宇基础30讲、考研竞赛凯哥、没咋了线代、田静句句真研 等考研资料全文本化。Markdown 纯文本 + LaTeX 公式，专为 AI / agent 直读与 RAG 设计。
Okapi BM25 information retrieval document scoring and search engine with document length normalization.
Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs with token overlap
AI Public Service Assistant for VAIC 2026 (Team Lead · MindSync). Grounded RAG, statutory verification & citizen workflows.
Hybrid AI system that uses OCR, ML, and RAG-powered LLMs to turn legal documents into plain-English explanations with risk flags.
Entity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.
Okapi BM25 information retrieval document scoring and search engine with document length normalization.
Cognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.
Open, independent benchmark on document parsing APIs and frontier VLMs for AI agents and RAG: does a struck-out clause in a redlined contract PDF survive the parse? Open source code + open data. LlamaParse, Reducto, Datalab, Extend, Pulse, Mistral OCR, GPT-6 Astra, Claude Fable 5.1.
用自然语言查询、分析和整理本地数据的 AI Agent
A production-grade, privacy-first desktop AI workstation & UI for local LLMs interfacing directly with Ollama.
轻量级 Wasm 向量数据库
Your AI agent says it's done. Assurance tells you what it didn't check.
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
AI-powered platform that transforms unstructured documents into connected, domain-aware knowledge graphs with contextual AI-assisted querying.
An MCP-native context bus that pushes updates to agents that subscribe to data using natural language.
The safety layer for the AGI era. Runtime guardrails for autonomous AI agents.
Telegram for your terminal and your AI agents: read, search, send and press bot buttons on your own account. MCP server included.
Model Context Protocol server with 260+ tools for AI agents
Cotlet: Give your AI agents your signed-in browser. Your own Chrome in the cloud for apps with no API, with one hosted MCP server and REST API on top.
Distributed swarm state snapshotting and transactional rollback engine restoring consistent states upon failure
Multi-vector heuristic prompt injection and jailbreak detector analyzing system overrides, delimiter breakouts, and base64 payload evasion.
Heuristic and pattern-based agent prompt injection sanitizer and LLM jailbreak firewall detecting adversarial jailbreaks, system prompt exfiltration, and tool hijacking.
Autonomous API schema fuzzing generator synthesizing boundary, injection, and mutation edge cases
Multimodal image smart cropper calculating saliency centroids and optimal responsive bounding boxes
Fast semantic query cache with fuzzy term similarity and canonical intent hashing to avoid duplicate LLM invocations and cache prompt responses safely
Full-duplex voice agent echo suppressor distinguishing user barge-in from speaker playback acoustic feedback
跨工作区独立人格、自适应风格与陪伴预设：为项目和对话分别维护人格与确认后的通用偏好，支持任意 DSH 已注册模型的子代理路由（含通过其他插件接入的 Codex、Claude Code）。
Web UI visual regression and bounding box displacement analyzer detecting layout shifts
Multi-agent round-robin debate coordinator driving thesis-antithesis cross-examination
Global e-commerce customs duty, HS code classification, and de minimis tariff calculator
Voice Activity Detection (VAD) audio silence boundary trimmer eliminating latency overhead
Web UI visual regression and bounding box displacement analyzer detecting layout shifts
Voice Activity Detection (VAD) audio silence boundary trimmer eliminating latency overhead
Discontinued experiment: an orchestrator that ran several Claude Code and Codex sessions in parallel on one project. No longer maintained.
Classical single-decree Paxos consensus engine with prepare, promise, accept, and commit phases for multi-agent distributed agreement
Multi-agent round-robin debate coordinator driving thesis-antithesis cross-examination
Conversational slot filling and intent requirement state machine generating targeted questions
Conversational slot filling and intent requirement state machine generating targeted questions