Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 176 of 465
A standalone agent harness in Rust: a provider-agnostic loop, MCP tools, a path jail and prompt-injection interlock, sandboxed shell, scheduled triggers, and an eval rig that grades the trace.
Lightweight OpenAI-compatible proxy for OpenRouter's free models. Automatically routes to the best available free (privacy-first) model with seamless failover.
AI Chat Webapp using cloudflare Stacks
Lightweight AI API cost tracking proxy - one-line base_url change, transparent token and cost monitoring.
Renderer toolkit for visualizing live AI agent and subagent orchestration graphs in Terminal, SVG, or HTML, laid out with ELK.
A platform-neutral playbook for self-dispatch, worker lanes, and bounded AI-agent delegation.
Give your agent a memory it can prove. One Python file: local SQLite vault, hybrid FTS5 + vector retrieval, Cloudflare-aware fetching, and a research loop whose [V]/[E]/[H] citations are machine-verified by CLI, not prompt-enforced.
Desktop orchestrator for Pi and Claude Code. Every stream of work gets its own git worktree, and an agent can drive the app itself — spawn sub-agents, delegate, integrate.
Agentic AI Engineer Learning Track - Build production multi-agent systems (agent loops, orchestration, RAG, eval, guardrails)
Agent 意图框架 — 把人话翻译成结构化意图+槽位+约束。输入规范化(两阶段) + 三层瀑布式意图识别(Code→Flash→Pro),80% 请求零 LLM 调用,10ms 内返回。650 测试全过。
Field-tested local AI stack optimizations for HermesAgent, LM Studio, and Qwen 3 models
Authoritative multi-agent software engineering coordinator with isolated Git worktrees, write scope locking, test verification, and serialized merge queue. (v0.1.0-beta).
DeepSeek Harness 跨会话 Agent 通信插件|Cross-session agent-to-agent messaging with offline delivery, receipts and session navigation for DeepSeek Harness.
AI Chatbot using OpenAI api
已停止维护。推荐改用 yetone/magpie:装好即用,把 ChatGPT / Claude / Copilot 订阅共享给 DSH 等所有工具
Twelve deep-dive notes on how AI agents actually work: the loop, tool use, MCP, context management, evals. Mental models over feature lists, every technical fact cross-checked against the official docs. Bilingual FR/EN.
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
Official SDKs, API clients, and CLI/MCP tools for Daytona, the secure and elastic infrastructure for running AI-generated code
Reusable starter kit for routing Hermes Agent through a local LiteLLM-based free/free-tier model router with clean aliases, fallback examples, systemd service templates, and terminal-first setup.
DeepSeek 桌面版客户端(社区构建,非官方):下载即用,无需 Node。Download-and-run desktop build of DeepSeek Harness — Electron shell, no npm required.
Scaffold, run & deploy production LangChain agents — frontend and agent in one command. Built-in proxy, 3 chat UIs, zero CORS.
Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server
Local-first desktop AI agent client. BYOK multi-provider chat (OpenAI- and Anthropic-compatible), multi-agent collaboration, embedded local-model runtime, encrypted local credentials. Tauri 2 + React 19 + Rust.
Tauri desktop app with Harness and official DeepSeek Chat modes. 基于 Tauri 重做,支持独立 Chat 登录与harness模式切换。
Local debugger for AI agents. Answer the question: "Why did my agent behave this way?" with visual replay, behavior diff, and full visibility into prompts, context, memory, retrieval, and tool calls. Open source. Works with Langchain.
## 👨💻 About Me Hi! I'm **Divanshu Singh**, an aspiring **Data Scientist and AI Developer** with a strong interest in Artificial Intelligence, Data Analytics and Software Development. I enjoy building practical projects that combine data, AI and automation. Currently, I'm working on **Pixotic AI Assistant**, a Telegram-based personal AI assi
Official implementation of SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models.
OpenAI-compatible API server powered by the GitHub Copilot SDK. It exposes the classic OpenAI endpoints so you can use standard OpenAI clients (including the official Python OpenAI SDK) against a local Copilot-backed proxy.
低价中转api_中转api为什么便宜_为什么AI中转站价格会便宜_Api中转平台_中转api推荐,推荐低价Chatgpt中转api_Openaiapi中转_Gemini中转api_Claude中转api
Codex额度悬浮窗:一眼查看 Codex 本周剩余额度 · Native float widget for weekly Codex quota
gguf code qwen qwen-coder codeqwen text-generation
Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.
gguf TeichAI qwen3 unsloth text-generation en
A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.
Grounded Memory Runtime — a runtime tool that links the Agent’s memory and facts
Lightweight standalone LLM inference engine. Single binary, no runtime deps. Serves GGUF models via Ollama/OpenAI/MCP APIs. Multi-agent orchestration, TUI, 21 built-in tools.
transformers gguf code codeqwen chat qwen
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem
safetensors gguf qwen2 bitnet quantization ternary
Provider-neutral dual-subagent orchestrator preset for DeepSeek Harness
A demonstration of the OpenAI Chat Completion API, featuring a Python Flask server and a Python client for interactive AI-powered conversations. This example showcases the GPT-4o model's ability to understand and generate human-like text in a conversational context.
Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+ tok/s on consumer GPU. Based on Qwen3.6-35B-A3B.
JupyterHub-style multi-user front for DeepSeek Harness (dsh): PAM login, per-user isolated instances, cookie-routed HTTP/WS proxy — zero modifications to dsh.
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation
DeepSeek-Desktop - DeepSeek AI with R1 reasoning, code generation, and unlimited conversations.
Autonomous AI agent framework — agents that browse, code, and create with tool use and memory
This is our micro-tiny GPT model (😁 we are still learning), built from scratch and inspired by the innovative approaches of Hugging Face Transformers and OpenAI architectures. Developed during our internship at 3D Smart Factory, this model showcases our committed efforts to create an advanced AI solution.
Multi-agent harness for OpenAI Codex with Jira-backed workflows, pause/resume, progressive capability loading, and frontend delivery for JavaScript projects.
Enterprise Capability Planning Compiler for governed, runtime-neutral business plans.
可自部署的团队协作式 AI 工作执行平台,基于 AgentScope Java:从对话目标到任务规划、Coding、Review、Human Gate 与 GitHub 交付,全程可观测、可恢复、可审计。Self-hosted team-execution platform for agentic coding: conversations become planned tasks, sandboxed coding runs and human-gated GitHub delivery.
Run local LLMs fully offline - chat, coding agent, image, music, video generation, knowledge/RAG, voice. Privacy-first, with GUI and CLI, no cloud required.
Open-source Django REST backend for the DARE Platform, with multi-LLM chat, RAG, MCP tools, AI workflows, and usage tracking.
Claude skills that make Opus 5 work like Fable 5
A lightweight, modern, and feature-rich Electron-based desktop client for Google Gemini, Google Search (AI Mode), DeepSeek, Kimi, Copilot, ChatGPT, Claude, Qwen, GLM by Z.ai and Deepseek Harness. It preserves the full capabilities of the official web interfaces while delivering a more native, efficient, and visually polished desktop experience.
Local, persistent memory for AI agents (MCP server). Plain JSON on your disk; fact-level search with an optional local semantic layer; corrections replace old facts; stale-value warnings; secrets kept out; a browser page to read, edit and merge it. One command installs it in Claude Code, Claude Desktop, Codex and Cursor.
Open-source self-improving AI agent for Windows: 5 native in-process ASI tools, one heartbeat over 10 subsystems (replaces ~84 cron jobs), and an A2A Global Mesh where every instance talks to every other instance. Apache-2.0, runs local.
A lightweight Python minifier that strips formatting and comments from JSON and code blocks to drastically reduce LLM prompt token costs.
Own your AI memory, don't rent it. A native Claude Code skill AND a standalone, zero-dependency MCP server over one local SQLite file. git clone and go — full-text knowledge graph, plain-markdown, you own the data.
Hands-on AI agent engineering course: LangChain, LangGraph, LangSmith, MCP, pgvector, pggraph, and Pydantic AI, taught through 200 small, linear lessons.
Explore AI Chatbot – an Android app powered by OpenAI. Engage in intelligent conversations with text-to-speech, speech-to-text, clipboard integration, and easy answer sharing. Maintain privacy with the clear chat option. The future of AI interactions is here in a compact, feature-rich package.
CrewAI / AutoGen hierarchical swarm task delegation & role governor
CoAgents / CopilotKit bidirectional human-agent workspace state sync coordinator
A2A standardized protocol capability negotiation & JWT auth handshake
Codex skill for orchestrating isolated GPT-5.6 Luna Max worker chats with GPT-5.6 Sol.
Pure TypeScript library for building AI agents with cognitive capabilities - perception, memory, reasoning, emotions, and adaptive learning
Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.
Synthetic monitoring and CI smoke tests for LLM inference endpoints.
Get notifications about leaks that might be bleeding your tokens. Based on real-time analysis on your coding agent sessions.
The incremental build system for AI applications.
OpenClaw skill: genpark foil
Dialectic multi-agent debate and cross-examination engine to eliminate hallucinations (AutoGen / ChatDev)
Hierarchical task breakdown into DAGs with worker matching & wave scheduling (CrewAI / MetaGPT)
LangGraph human-in-the-loop breakpoint pause & state mutation patcher
Dynamic multi-tool execution dependency DAG topological sorter (Semantic Kernel)
Lossless context packaging and state handoff protocol between autonomous subagents (OpenAI Swarm / LangGraph)
Hierarchical subagent resource governor and token quota sentinel (CrewAI / LangSmith)
Multi-agent proposal deliberation and Byzantine-fault-tolerant consensus voting protocol (AutoGen / LangGraph)
Access DeepSeek V3 and R1 Pro API without limits via shared API key rotation.
GenPark AI Agent Skill - Hierarchical supervisor-worker swarm coordinator, sub-task partitioner, and synthesized response aggregator.
GenPark AI Agent Skill - Multi-agent conversational turn orchestrator, round-robin handoff tokens, and speaker selection router.
GenPark AI Agent Skill - Raft distributed consensus state machine with leader election, log replication, and deterministic commit index synchronization across agent swarms.
GenPark AI Agent Skill - Vector clock and Lamport logical timestamp engine tracking causal dependencies and detecting concurrent race conditions across asynchronous agents.
GenPark AI Agent Skill - Weighted Borda count and Condorcet preference aggregation engine ranking candidate agent proposals by credibility-weighted peer ballots.
GenPark AI Agent Skill - Practical Byzantine Fault Tolerance (PBFT) quorum consensus engine tolerating arbitrary malicious, adversarial, and hallucinating agents.
GenPark AI Agent Skill - Raft consensus leader election state machine, term arbitration, randomized heartbeat timers, and split-vote resolver.
GenPark AI Agent Skill - Blackboard architecture shared state store, atomic key-value transactions, and pub-sub topic event broadcast.
GenPark AI Agent Skill - Parallel branch fanout and barrier join coordinator for multi-agent DAG subtasks with isolated error containment.
GenPark AI Agent Skill - Anti-entropy gossip protocol and epidemic rumor-spreading state synchronizer propagating shared knowledge across dynamic agent swarms.
GenPark AI Agent Skill - Multi-tier model cascading router dynamically selecting optimal models (e.g. Small vs Medium vs Large) based on task complexity, cost budgets, and SLA constraints.
GenPark AI Agent Skill - Pairwise Bradley-Terry and Elo rating tournament engine for ranking multi-agent strategies, prompt mutations, and generated tool solutions.
GenPark AI Agent Skill - Continual learning experience replay buffer with streaming reservoir sampling and priority weighting to balance past vs new agent trajectories.
GenPark AI Agent Skill - Detects LLM hallucinations and confabulations by clustering sampled responses into semantic equivalence classes and computing semantic entropy.
GenPark AI Agent Skill - Prioritized experience replay buffer for agent reinforcement fine-tuning (RFT / GRPO) with advantage estimation and importance sampling weights.
GenPark AI Agent Skill - Hierarchical Task Network (HTN) decomposition engine recursively expanding compound high-level goals into primitive executable action sequences.
GenPark AI Agent Skill - Knowledge distillation teacher-student loss engine with temperature-scaled Kullback-Leibler divergence for continual model compression and capability preservation.
GenPark AI Agent Skill - Direct Preference Optimization (DPO) implicit reward calculation, reference policy log-ratio tracking, and pairwise preference loss evaluation.
GenPark AI Agent Skill - Belief revision logic engine (AGM postulates) detecting factual and logical contradictions, pruning obsolete beliefs, and preserving consistent world states.
GenPark AI Agent Skill - Speculative decoding simulation engine coordinating small draft model speculative token generation and large target model parallel rejection sampling verification.