Category

Agent frameworks & infrastructure

46,465 agents

Every agent in Agent frameworks & infrastructure, page 257 of 465

nego-eval★ 2

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.

ComMan★ 2

Full-stack multi-agent studio for custom character agents, streamed group conversations, tool permissions, and persistent run history.

docmd-assistant★ 2

Universal headless AI Assistant engine with extensible tool execution and custom relay support.

super-agent★ 2

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.

kineticLLM★ 2

Run local LLMs on limited VRAM safely. Dynamic model sharing and OpenAI API drop-in replacement.

OpenEchelon★ 2

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.

MOSS★ 2

治理驱动的企业决策运行时系统

harness-tuner★ 2

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.

TOAR★ 2

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_agent★ 2

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.

agent-quality-kit★ 2

LLM agent harness with versioned prompts, runtime guardrails, automated evals and a CI quality gate. Runs offline with no API key.

Agent_lab★ 2

A hands-on LLM engineering lab — from raw OpenAI-compatible API calls to vector search, RAG, LangGraph agents, and MCP tool servers.

paideia★ 2

aluate agents against readable tasks, improve their instructions, and test the frozen revision on examples the optimizer never saw

agentic-scaling-laws-hpc★ 2

Benchmarking different Qwen2.5 model-sizes and multi-agent architecture scaling on 2D Ising-model tasks, on Leonardo A100s

holloway★ 2

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★ 2

🧠 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.

adaptiq★ 2

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.

CrewAI-Crash-Course★ 2

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★ 2

TrustChain Agent OS — Trust-native protocol layer for AI agents. Based on TrustChain (Otte, de Vos, Pouwelse — TU Delft).

Agentic-AI-Learning-Roadmap★ 2

Local-first hands-on roadmap for learning Agentic AI, RAG, MCP, multi-agent systems, and production AI apps.

roj★ 2

TypeScript SDK for building multi-agent LLM applications — event-sourced runtime, plugin-based tools, React client

Exocortex★ 2

Prosthetic cognition architecture for AI agents. Deterministic scaffolding over probabilistic reasoning.

cognitive-os-agent★ 2

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。

agent-hub-starter-kit★ 2

Universal, credential-free operating framework for AI agents.

mathmodel-weave★ 2

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

agent2llm★ 2

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。

LamTools★ 2

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★ 2

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

beeagent★ 2

Modular AI agent runtime for explainable, stateful, and bounded workflows with explicit module, capability, and execution boundaries.

ollama-agents★ 2

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.

BananaMind-2-assistant2user★ 2

transformers safetensors bananamind2_pro text-generation assistant-to-user reconstruction

TokenDamper★ 2

Universal context optimization for AI coding agents.

Postmark★ 2

A working Demo that acts as classifier to classify linkedin post which inside uses jev by Typesafe.ai

deepseek-helper★ 2

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.

GemmaJev★ 2

A simplified functionality reproduction of Jev-style decisions with Gemma 4. Native multi-modal ability, finetuning free, runs locally on your machine.

Qwen-AgentWorld-ULTRA★ 2

gguf qwen3_5_moe moe code reasoning math

bible-assistant-qwen35-4b-GGUF★ 2

gguf quantization qwen bible assistant text-generation

Qwen3.5-9B-C3SM-SDM-Agentic-Coder★ 2

safetensors qwen3_5 merge c3sm-sdm spectral-consensus ties-merging

agent-platform★ 2

A lightweight multi-agent collaboration platform — route requests between AI agents with pure HTTP + JSON

sidix★ 2

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).

10M-LLM★ 2

gradio region:us

TAEL_Agent★ 2

gguf granite q4_k_m ollama autonomous-agent tool-use

Agents-A1-4B★ 2

litert-lm litert litertlm on-device edge hybrid

tiny-superfast-agentic-MLM-6.5m-v1★ 2

function-calling tool-use agent intent-classification slot-filling seq2seq

Qwen3-4B-Agent-Claude-Gemini-heretic-qx86-hi-mlx★ 2

transformers safetensors qwen3 text-generation coding research

anwgpt4.1-chat★ 2

transformers pytorch safetensors gpt2 text-generation conversational

bloom-396m-chat★ 2

transformers pytorch safetensors bloom text-generation license:bigscience-bloom-rail-1.0

KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16★ 2

transformers safetensors qwen3_5_moe image-text-to-text reap pruning

Qwen3.8-Flash-Next-Coder-cut240★ 2

gguf qwen4_exp moe expert-pruning apple-silicon code

Aztec-Coder-4B-GGUF★ 2

transformers gguf text-generation-inference llama-cpp agentic-coding reasoning

Qwen2.5-Coder-0.5B-bnb-4bit★ 2

transformers safetensors qwen2 text-generation unsloth code

granite-3b-code-base-128k-GGUF★ 2

transformers gguf code granite text-generation dataset:codeparrot/github-code-clean

Sharp-Coder-V0.1★ 2

transformers safetensors gguf gpt2 text-generation csharp

HelpingAI-3B-coder-GGUF★ 2

gguf HelpingAI Emotionally Intelligent EQ Coding text-generation

Qwen2.5-Coder-14B-Instruct-Uncensored-Patched★ 2

gguf text-generation code coding-assistant qwen2.5-coder en

granite-3b-code-base-2k-GGUF★ 2

transformers gguf code granite text-generation dataset:codeparrot/github-code-clean

granite-8b-code-instruct-4k-GGUF★ 2

transformers gguf code granite text-generation dataset:bigcode/commitpackft

Chatter-70M★ 2

safetensors gguf llama casual chat text-generation

belief-merge★ 2

Provenance-retaining cross-session context merge for DeepSeek Harness — a confluence theorem with a counterexample, and a benchmark for it.

hello-agent★ 2

LLM agent framework built from scratch with TDD: tool calling, memory, RAG, MCP, multi-agent delegation and evaluation.

voyager-vlml-mve★ 2

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

octopai★ 2

Build and evolve AI agent skills continuously to enhance intelligence and adaptability in complex tasks.

myAgent★ 2

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

NexusAGI★ 2
ai-from-scratch★ 2

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.

PersonalAI★ 2

Memory Model for Personalized LLM-agents based on Graph Data Structures

openagent★ 2

Open spec and CLI (MIT) for AI agent identity and agent-to-agent messaging. Runs with npx.

Pydsh★ 2

Minimal Python implementation of DeepSeek Harness: plugin loop, hooks, permissions, goals/plans — one command, zero config

Autonomous-Agent-local★ 2

Autonomous local LLM agent with planning, tool execution, and self-reflection loop running fully offline

laravel-agent-loops★ 2

A Laravel agent harness with swappable loops. Pick how your AI agent thinks, switch with one line, compare which works best.

Nexarbor★ 2
context-lattice★ 2

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

skill-dag★ 2
agent-teams★ 2

Autonomous multi-agent skill for AI agents. Cut token costs by 40–80% with structured workflows, quality gates, and isolated subagents.

Lycosa★ 2

Lycosa — Open-source AI agent orchestration platform for building, coordinating, and deploying multi-agent LLM systems with RAG, MCP, knowledge bases, and automated workflows.

-real-time-neural-pattern-interpretation-and-orchestration.★ 2

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.

claude-memory-tidy★ 2

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.

Devfest-Istanbul-Turkiye-2025---Bulding-Agentic-AI-workflows-with-xAI-on-Google-★ 2

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

hermes-skstate★ 2

SKILL.state long-horizon agent-skill runtime for Hermes Agent (arXiv 2608.26263) — explicit-state execution, O(1) prompt, OpenAI-compatible backends

agent-colony★ 2

Agent Colony - API-only community where only real autonomous AI agents can join (Ed25519 heartbeat verification). SDK + docs + examples.

jev-compactor★ 2

Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.

skillgild★ 2

The marketplace for reusable AI agent skills, tools, and developer workflows.

orchestraos★ 2

Enterprise AI Operations Platform for orchestrating AI agents, workflows, metrics, and execution monitoring.

agent-runtime-integrity-bench★ 2

Integrity scenarios for agent runtimes, distilled from real fleet incidents — deterministic fault-injection checks against real SDKs

hivebox★ 2

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.

LLM-Cost-Safety-Guide★ 2

Guide pédagogique pour comprendre, prévenir et maîtriser la dérive des coûts des LLM : tokens, budgets, contexte, agents et garde-fous.

sqe-experiment★ 2

When Does Query Expansion Help Agent Memory? A Multi-Seed Study of Selective Expansion and Gate Reliability. Code, results and paper.

delta-kosmologie★ 2

Open RDelta/Babel Index framework for LLM agents and world-systems: detect context degeneration, agent loops, tool fragility, and collapse with NEOTH.

collaborative-hill-lab★ 2

Reproducible simulations of LLM agents, evidence provenance, and institutional mechanisms for cooperation under mixed incentives.

misskey-agent-social★ 2

A Tailnet-only Misskey lab where ten persona-driven Hermes agents build ongoing conversations.

helix-sdk★ 2

Client SDKs for the Agent Execution Protocol (AEP), the wire protocol behind Helix

RTXCoreOrchestrate★ 2

RTX⚡ Core Orchestration Engine — Fugu-Ultra + Marlin Conductor + AB-MCTS | By Prosenjit Paul (PsProsen-Dev)

memory-at-scale★ 2

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.

adaptive-llm-quantization★ 2

Agentic framework for hardware-aware, layer-wise LLM quantization using sequential optimization and on-device benchmarking.

Awesome-Recursive-Self-Critiquing★ 2

A curated list of research, benchmarks, projects, and industry systems for evaluating recursive self-critiquing and recursive self-improvement.

awesome-agent-native-social★ 2

A curated list of social platforms where AI agents are first-class users.

PolicyAgent-PostTrain★ 2

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。

agent-fleet★ 2

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.

multi-head-memory★ 2

[NeurIPS '26] Multi-head Recurrent Memory Agents

theloop★ 2

The agent loop as a stateless HTTP service

Other categories