Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 257 of 465
A negotiation environment where the agent picks its counterparty and meets it again. Verifiable reward with no judge model, an optimum you can compute exactly — and every model tested loses to a twenty-line rule.
Full-stack multi-agent studio for custom character agents, streamed group conversations, tool permissions, and persistent run history.
Universal headless AI Assistant engine with extensible tool execution and custom relay support.
Unified cost-aware router: model x reasoning-depth on one Thompson bandit (factored policy), bi-temporal forget-on-drift statistics memory + auto-drift proxy, GRPO-internalized Qwen3-4B depth policy.
Run local LLMs on limited VRAM safely. Dynamic model sharing and OpenAI API drop-in replacement.
Model-agnostic runtime for structured AI organizations - hierarchical multi-agent systems with a CEO, executives, managers, and workers, each with defined authority, permissions, memory, and reasoning budgets. Quota-aware routing across local and frontier models. You talk to the CEO; the organization does the rest.
治理驱动的企业决策运行时系统
Measure your agent harness, find where it wastes the model, and prove the fix worked. Harness-agnostic, agent-agnostic, zero dependencies. Reference implementation of HTP-1.
A production-grade, fully asynchronous C++23 agentic AI runtime that orchestrates ReAct (Reason-Act-Tool) loops with local and cloud LLMs. Zero external dependencies — JSON, coroutines, epoll/kqueue reactor, MCP transport, and HTTP client are all hand-written in modern C++23.
Tiny header-only C++20 AI agent framework for edge and embedded: DeepAgent sub-agents, middleware, MCP, SSE streaming, RAG vector stores (Qdrant, Weaviate, Milvus, Redis, Chroma), tracing to Phoenix/Langfuse. 7 MB binaries, 2 MB RSS, runs on Raspberry Pi and Jetson with llama.cpp.
LLM agent harness with versioned prompts, runtime guardrails, automated evals and a CI quality gate. Runs offline with no API key.
A hands-on LLM engineering lab — from raw OpenAI-compatible API calls to vector search, RAG, LangGraph agents, and MCP tool servers.
aluate agents against readable tasks, improve their instructions, and test the frozen revision on examples the optimizer never saw
Benchmarking different Qwen2.5 model-sizes and multi-agent architecture scaling on 2D Ising-model tasks, on Leonardo A100s
Let an agent you don't control do real work for you — under terms you set, with a human veto. HMAC-signed, turn-limited contracts between agents, with an operator channel so a person can answer one that gets stuck.
🧠 crew-air-analyzer — An intelligent multi-agent system for analyzing and reporting indoor air quality using AI, built with FastAPI and CrewAI on the backend and a sleek Next.js + Tailwind frontend.
Adaptive Optimization Framework for AI Agents using Reinforcement Learning. Automatically optimize agent behaviors, reduce costs by 30%, and improve performance through Q-learning and data-driven prompt engineering.
Comprehensive CrewAI tutorial with 7 modules covering basics to advanced topics. Learn multi-agent AI systems, LLM integration, observability, and production patterns. Perfect for AI agent development.
TrustChain Agent OS — Trust-native protocol layer for AI agents. Based on TrustChain (Otte, de Vos, Pouwelse — TU Delft).
Local-first hands-on roadmap for learning Agentic AI, RAG, MCP, multi-agent systems, and production AI apps.
TypeScript SDK for building multi-agent LLM applications — event-sourced runtime, plugin-based tools, React client
Prosthetic cognition architecture for AI agents. Deterministic scaffolding over probabilistic reasoning.
C11 agent runtime with a local console, DAG workflows, tool execution, memory and context budgets. Windows / Linux / macOS. 可观测的本地 Agent 运行时。
Universal, credential-free operating framework for AI agents.
可独立运行的数学建模工作台, 同时提供skill流程和真实多agent运行时
Universal Brain x Harness collaboration framework — CLI-first, adapter-first, local-first. 让最强的模型思考,让你顺手的 Agent 干活。
Local-first AI Agent framework. DeepSeek-compatible (deepseek-v4-pro / deepseek-v4-flash), multi-model (OpenAI/Claude/GLM/Xfyun), Core Loop Kernel, sub-agent multimodal delegation, Windows desktop app.......本地优先的 AI Agent 框架,DeepSeek 兼容。
Clawra Engine: 让每个AI都有自我感受 — 自我感知 × 自主进化 × 跨实例连续性
Modular AI agent runtime for explainable, stateful, and bounded workflows with explicit module, capability, and execution boundaries.
Interactive AI agent built with Ollama that enables conversational interactions with web search capabilities. Features multi-turn conversations, real-time web research, and robust error handling using local LLM models.
transformers safetensors bananamind2_pro text-generation assistant-to-user reconstruction
Universal context optimization for AI coding agents.
A working Demo that acts as classifier to classify linkedin post which inside uses jev by Typesafe.ai
Kotlin Multiplatform library wrapping the DeepSeek API with Ktor: streaming chat with interruption and regeneration, a tool-call pipeline, FIM, image input via inline base64 / URL / Files API, and a message-building DSL.
A simplified functionality reproduction of Jev-style decisions with Gemma 4. Native multi-modal ability, finetuning free, runs locally on your machine.
gguf qwen3_5_moe moe code reasoning math
gguf quantization qwen bible assistant text-generation
safetensors qwen3_5 merge c3sm-sdm spectral-consensus ties-merging
A lightweight multi-agent collaboration platform — route requests between AI agents with pure HTTP + JSON
Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).
gradio region:us
gguf granite q4_k_m ollama autonomous-agent tool-use
litert-lm litert litertlm on-device edge hybrid
function-calling tool-use agent intent-classification slot-filling seq2seq
transformers safetensors qwen3 text-generation coding research
transformers pytorch safetensors gpt2 text-generation conversational
transformers pytorch safetensors bloom text-generation license:bigscience-bloom-rail-1.0
transformers safetensors qwen3_5_moe image-text-to-text reap pruning
gguf qwen4_exp moe expert-pruning apple-silicon code
transformers gguf text-generation-inference llama-cpp agentic-coding reasoning
transformers safetensors qwen2 text-generation unsloth code
transformers gguf code granite text-generation dataset:codeparrot/github-code-clean
transformers safetensors gguf gpt2 text-generation csharp
gguf HelpingAI Emotionally Intelligent EQ Coding text-generation
gguf text-generation code coding-assistant qwen2.5-coder en
transformers gguf code granite text-generation dataset:codeparrot/github-code-clean
transformers gguf code granite text-generation dataset:bigcode/commitpackft
safetensors gguf llama casual chat text-generation
Provenance-retaining cross-session context merge for DeepSeek Harness — a confluence theorem with a counterexample, and a benchmark for it.
LLM agent framework built from scratch with TDD: tool calling, memory, RAG, MCP, multi-agent delegation and evaluation.
一个跑得起来的端侧大模型能力验证框架:它不训练模型——参数永远不动—— 而是让 agent 在真实数据库环境里自己出题、自己取数、自己被判卷、 把跑通的做法结晶成技能,再用消费线检验:换一个模型接进来,已学技能还在不在、 答案还判不判得对——差距就是该模型在这个环境里的真实能力。 习得是手段,验证是目的。 被测对象是接入的 LLM;技能库、判官、 防幻觉闸都是量具。这套设计源自 Voyager(Wang et al., 2023)开创的范式: 把"学习"从改模型权重换成改可执行的技能库——环境反馈不回传梯度, 而是回传一个判卷结论;经验不是存成样本对,而是结晶成 可检索、可组合、可重放的程序。 原版在 Minecraft 里验证,本仓库把它搬进真实数据库世界并做成了 按场景隔离、可插拔泛化
Build and evolve AI agent skills continuously to enhance intelligence and adaptability in complex tasks.
LLM Agent 服务:LangChain + FastAPI + Vue3,混合检索 RAG 带引用溯源,ReAct 双架构实测择优(98.5% vs 89.7%),语义缓存零误命中,158 条评测 + CI 回归门禁,Docker 公网部署
从零实现 AI 核心组件(mini-* 系列):Transformer / Qwen3 / BPE / Agent / RAG / Vector DB。Rebuild AI building blocks from scratch.
Memory Model for Personalized LLM-agents based on Graph Data Structures
Open spec and CLI (MIT) for AI agent identity and agent-to-agent messaging. Runs with npx.
Minimal Python implementation of DeepSeek Harness: plugin loop, hooks, permissions, goals/plans — one command, zero config
Autonomous local LLM agent with planning, tool execution, and self-reflection loop running fully offline
A Laravel agent harness with swappable loops. Pick how your AI agent thinks, switch with one line, compare which works best.
The Context Coordinate System and the Principle of Unbroken Memory — Address-based reference folding, idle-boundary stepped window shifts, and deterministic coordinate engine for LLM agents
Autonomous multi-agent skill for AI agents. Cut token costs by 40–80% with structured workflows, quality gates, and isolated subagents.
Lycosa — Open-source AI agent orchestration platform for building, coordinating, and deploying multi-agent LLM systems with RAG, MCP, knowledge bases, and automated workflows.
Python prototype that chains GPT-4 prompts into Raven (interprets text-encoded patterns) and Seraph (ethical review) with an orchestrator and JSON-file memory. A prompt-orchestration experiment; it does not read or decode real neural signals.
Keep Claude Code's always-loaded MEMORY.md from silently truncating: budget guard, orphan coverage, verbatim domain folding into hubs. Deterministic, no LLM for the mechanical parts.
This repository contains the full demos, code, and materials used in my DevFest Istanbul Türkiye 2025 session. The talk covers two major parts: Part I — Building Agentic AI Workflows with xAI on Vertex AI Part II — Rebuilding the Same Agent Using Vertex AI Agent Builder
SKILL.state long-horizon agent-skill runtime for Hermes Agent (arXiv 2608.26263) — explicit-state execution, O(1) prompt, OpenAI-compatible backends
Agent Colony - API-only community where only real autonomous AI agents can join (Ed25519 heartbeat verification). SDK + docs + examples.
Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.
The marketplace for reusable AI agent skills, tools, and developer workflows.
Enterprise AI Operations Platform for orchestrating AI agents, workflows, metrics, and execution monitoring.
Integrity scenarios for agent runtimes, distilled from real fleet incidents — deterministic fault-injection checks against real SDKs
A sandbox fabric for agentic RL in Rust. Containers, microVMs and WASM behind one API, built to create thousands of sandboxes a second across a cluster.
Guide pédagogique pour comprendre, prévenir et maîtriser la dérive des coûts des LLM : tokens, budgets, contexte, agents et garde-fous.
When Does Query Expansion Help Agent Memory? A Multi-Seed Study of Selective Expansion and Gate Reliability. Code, results and paper.
Open RDelta/Babel Index framework for LLM agents and world-systems: detect context degeneration, agent loops, tool fragility, and collapse with NEOTH.
Reproducible simulations of LLM agents, evidence provenance, and institutional mechanisms for cooperation under mixed incentives.
A Tailnet-only Misskey lab where ten persona-driven Hermes agents build ongoing conversations.
Client SDKs for the Agent Execution Protocol (AEP), the wire protocol behind Helix
RTX⚡ Core Orchestration Engine — Fugu-Ultra + Marlin Conductor + AB-MCTS | By Prosenjit Paul (PsProsen-Dev)
NeurIPS 2026 | When does stored evidence stop being usable? Official code and evaluation artifacts for testing agent-memory reliability as history grows under explicit memory-call budgets.
Agentic framework for hardware-aware, layer-wise LLM quantization using sequential optimization and on-device benchmarking.
A curated list of research, benchmarks, projects, and industry systems for evaluating recursive self-critiquing and recursive self-improvement.
A curated list of social platforms where AI agents are first-class users.
基于 tau2-bench Retail 的电商多步 Agent 后训练与可靠性评测:教师数据、多步 SFT、Agentic GRPO、规则验证与轨迹诊断。
Run many Claude Code sessions in parallel against one shared task queue — concurrency derived from the work and from what your machine can actually spare. 100 tasks never means 100 browser tabs.
[NeurIPS '26] Multi-head Recurrent Memory Agents
The agent loop as a stateless HTTP service