中文

Agent infrastructure

451 projects · page 5 / 5

401-451 of 451
Project
Added
Created
Stars
401
tensorsharpgemmainferenceinference-engine
A .NET inference engine for local GGUF models offering a CLI, browser chat and Ollama/OpenAI-compatible APIs with CPU, CUDA, Metal and Vulkan backends.zhongkaifu
2026-07-25
2026-04-03
679 stars
402
NadirClawaicost-optimizationgemini
A self-hosted LLM router and cost optimizer. It classifies prompts, sends simple ones to cheaper or local models, verifies answers, escalates when needed, and exposes OpenAI- and Anthropic-compatible endpoints for coding agents and chat clients.NadirRouter
2026-07-22
2026-02-11
667 stars
403
termioadeagenticai-agents
Termio is a terminal-first agentic development environment that manages parallel CLI coding agents, keeps sessions alive in a daemon, notifies when an agent needs attention, and mirrors sessions to iPhone.termio-sh
2026-09-17
2026-05-23
660 stars
404
kookyagentai-codingclaude
Kooky is a minimal macOS terminal built for AI coding, with workspace tabs, split panes, one-click launches for many coding agents, session resume, and live agent activity status.iAmCorey
2026-07-26
2026-05-08
656 stars
405
locate-anything.cpp
A fast C++ ggml inference port of NVIDIA LocateAnything-3B for open-vocabulary detection on CPU and GPU.mudler
2026-08-02
2026-06-10
656 stars
406
lollms_hubollamaproxysecurity
A universal AI gateway that unifies multiple Ollama, vLLM, llama.cpp and OpenAI-compatible backends behind one managed API with authentication, rate limiting, routing and usage analytics.ParisNeo
2026-08-27
2024-01-15
649 stars
407
headroom-desktopaianthropicclaude-code
Headroom Desktop is a menu-bar app for macOS, Windows, and Linux that routes Claude Code, Codex, OpenCode, and Grok Build through a local proxy, reversibly compressing tool output and logs to roughly halve token costs while showing savings analytics.gglucass
2026-08-27
2026-03-30
649 stars
408
uncensored-ai-apiuncensored-aiabliterated-modelsai-models
Official docs and code samples for UncensoredLabs, a hosted OpenAI-compatible API and browser chat for uncensored DeepSeek and GLM text models, including pricing, streaming and client setup guides.UncensoredLabs
2026-11-04
2026-11-01
649 stars
409
pooledbrowserdistributed-inferenceinference
Pooled runs large open models across browsers by splitting model layers among devices in a room over WebRTC and WebGPU. Users open a link to chat or use Code mode, and the room can expose an OpenAI/Anthropic-compatible API to other tools.Nehanth
2026-09-29
2026-09-01
647 stars
410
managed-agentsagent-observabilityagent-runtimeai-agents
A local-first runtime for production AI agents, providing persistent sessions, sandboxed execution, tool governance, credential vaults, memory, audit trails, and a console.sandbaseai
2026-07-24
2026-07-11
643 stars
411
Lynkrclaudeclaudecodedatabricks
Lynkr is an LLM gateway for AI coding tools. It routes requests across local and cloud providers by task complexity, compresses tool output, caches repeated prompts, and shows spend and routing analytics, all without changing your editor or agent.Fast-Editor
2026-08-27
2025-12-03
640 stars
412
ollitert
An Android app that runs LLMs fully on-device and serves them over your local network via an OpenAI-compatible API.nightmean
2026-08-31
2026-04-06
633 stars
413
harness-scoreai-agentsai-assisted-developmentcli
Harness Score is a deterministic CLI that audits the context files, skills, hooks, sensors and CI around an AI coding agent, scoring repository harness maturity from L0 to L4 with concrete fixes.paladini
2026-07-29
2026-07-11
630 stars
414
dsh-plugin-subscriptionsai-agentchatgptclaude
A DeepSeek Harness plugin that routes ChatGPT, Claude, and Grok subscriptions as LLM providers via OAuth.V1ki
2026-08-19
2026-08-14
620 stars
415
skillhub-desktopagentskillsaidesktop-app
SkillHub Desktop is a desktop app for managing AI coding skills across tools. Browse a catalog, install or create skills, and sync them between Claude Code, Cursor, OpenCode, and others.skillhub-club
2026-08-27
2026-01-16
602 stars
416
cc-lensclaude-codeclaude-skillsai-tools
A local analytics dashboard for Claude Code that visualizes sessions, tokens, costs, and tool usage from your own machine.Arindam200
2026-06-26
2026-03-14
601 stars
417
agentlyticsai-coding-assistantanalyticsclaude-code
A local-first analytics dashboard that unifies AI coding sessions from 17 editors, tracking costs, models, tools and activity, with an optional relay server for team-wide session sharing.f
2026-08-27
2026-03-07
597 stars
418
cl-benchbenchmarkcontext-learninglanguage-model
A benchmark suite for measuring whether language models can learn new knowledge from context, with expert-annotated tasks, rubrics, inference scripts, and evaluation code.tencent-hunyuan
2026-07-22
2026-01-23
595 stars
419
spoolai-agentsclaude-codecodex
A tool to store, share and resume real AI coding sessions as readable web pages, with team spaces, secret scanning and native continuation.paperboytm
2026-08-27
2026-03-27
593 stars
420
agentboxclaudecodexdocker
AgentBox teleports a project into an isolated local or cloud VM and runs multiple coding agents in parallel, with snapshots, pause/resume, a browser, and remote access built in.madarco
2026-07-26
2026-05-12
583 stars
421
pixtuoidai-agentsclaude-codecli
A terminal pixel-art office that visualizes AI coding agent sessions as coworkers, showing who is working, waiting for approval, done or burning tokens at a glance.pixtuoid
2026-10-21
2026-05-21
576 stars
422
vllm-moet
A vLLM patch and hand-written kernels for serving frontier MoE models on consumer Blackwell GPUs via aggressive quantization and tiered residency.kacper-daftcode
2026-07-10
2026-06-15
574 stars
423
dubbo-go-pixiudubboproxydubbo-cluster
Dubbo-Go-Pixiu is a high-performance AI and API gateway that unifies access to LLMs and MCP servers, bridges HTTP, gRPC and Dubbo protocols, and adds plugin-based governance.apache
2026-08-27
2020-01-16
574 stars
424
kiro.rs
A Rust API gateway that translates Anthropic and OpenAI-compatible requests to Kiro/Amazon Q, with credential pooling, proxy rotation, usage accounting, and an admin console.zyphrzero
2026-07-24
2026-05-21
569 stars
425
lot-mapagent-observabilityai-agentsclaude
A Claude Code plugin that draws a live map of the agent's work beside the chat, lighting up tool calls, model steps, hooks, skills and subagents as they happen.alexeyw
2026-11-12
2026-11-09
569 stars
426
omg.devai-agentsclaude-codecodex
A remote control and session manager for coding agents such as Claude Code, Codex, Cursor, and OpenCode. It lets you assign tasks from a phone or web UI, follow progress, and get notified when work finishes.BennyKok
2026-10-28
2026-06-17
559 stars
427
corallinebashclaudeclaude-code
Coralline is a Powerlevel10k-inspired statusline for Claude Code. It renders directory, git, model, context, rate-limit and cost segments, themed subagent rows and optional burn-rate forecasting, installed entirely locally with no API calls.Nanako0129
2026-08-27
2026-06-12
554 stars
428
amd-strix-halo-vllm-toolboxes
An Ubuntu container toolbox for serving LLMs with vLLM on AMD Strix Halo with clustering and easy launch.kyuz0
2026-06-30
2025-09-03
551 stars
429
TavilyProxyManagerproxytavily
A transparent reverse proxy for the Tavily API that pools multiple API keys behind one master key, with quota-aware rotation, failover, an MCP endpoint and a web dashboard.xuncv
2026-08-27
2026-01-26
551 stars
430
yepanywhere
A self-hosted mobile-first web UI for supervising Claude Code and Codex sessions, approvals, diffs, and devices remotely.kzahel
2026-06-26
2025-12-28
550 stars
431
emilia-protocolagent-securityagentic-aiai-agents
Authority and security infrastructure for AI agents that checks exact authorization before consequential tool calls and produces verifiable evidence.emiliaprotocol
2026-08-08
2026-03-13
550 stars
432
heardai-agentsclaude-codecodex
Heard is a macOS menu-bar app that speaks short summaries of what your coding agents are doing, so you can step away and still know when Claude Code or Codex finishes, fails, or needs approval. The open-source engine runs local Kokoro voices or your own cloud voice keys.heardlabs
2026-11-17
2026-04-24
550 stars
433
clawlessagent-runtimeaiai-agents
ClawLess is a serverless, browser-based runtime for Claw AI agents built on WebContainers. It provides a fully sandboxed Node.js environment with an editor, terminal, YAML policy engine, audit logging and a pluggable SDK, all without a backend.open-gitagent
2026-08-27
2026-03-19
545 stars
434
MioIslandai-codinganthropicclaude
A macOS Dynamic Island app for monitoring, approving, and jumping into Claude Code and other AI coding agent sessions from the notch, with iPhone sync and remote launch.MioMioOS
2026-08-27
2026-04-01
544 stars
435
vibearoundai-agentai-toolsvibe-coding
An all-in-one desktop hub for launching and managing coding agents with model bridging, session continuity and remote access.jazzenchen
2026-08-10
2026-02-23
539 stars
436
token-trackerai-agentclaude-codecli
A local token and cost tracker for Claude Code, Codex and Kimi Code, adding status lines, GitHub-style heatmaps, a session sidebar and daily or weekly usage reports, all stored on your machine.stormzhang
2026-08-27
2026-05-08
536 stars
437
ClawWork
A local-first desktop and PWA workspace for OpenClaw that runs parallel agent tasks, stores artifacts durably, and coordinates multi-agent teams from one UI.clawwork-ai
2026-08-27
2026-03-12
534 stars
438
krasiscpu-inferencegguf-model-supportgpu-inference
A local LLM runtime for running very large MoE models on consumer NVIDIA GPUs, with quantization caches and an OpenAI-compatible API.brontoguana
2026-07-27
2026-02-09
530 stars
439
clshclaude-codedeveloper-toolsnode-pty
A PWA that gives you real terminal access to your machine from a phone or tablet, letting you run and watch AI coding agents such as Claude Code remotely.my-claude-utils
2026-08-27
2026-03-13
529 stars
440
xybridai-gamesedge-aiios
A cross-platform on-device AI runtime and SDK collection for running LLMs, speech recognition and text-to-speech locally in mobile apps, desktop software and games.xybrid-ai
2026-10-25
2025-12-13
524 stars
441
better-agent-terminalai-agentanthropicclaude
A multi-workspace terminal aggregator with built-in Claude Code and Codex agent panels, file browsing, Git views, snippets, and remote or mobile access.tony1223
2026-09-10
2025-12-17
523 stars
442
gemini-cli-desktopdesktopgeminigemini-api
Gemini CLI Desktop is a desktop and web GUI for Gemini CLI and Qwen Code, adding project management, visual tool approvals, diff viewing, conversation search, and MCP server management.Piebald-AI
2026-09-12
2025-07-27
522 stars
443
agent-hud-openai-agentsclaude-codecodex
A desktop HUD for Claude Code, Codex and 25+ coding agents that shows quotas, token usage and sessions at a glance, lets you approve requests, and syncs with iPhone and Apple Watch.jazzenchen
2026-11-15
2026-10-22
516 stars
444
willow-inference-servercudadeep-learningllama
Willow Inference Server is a self-hosted, CUDA-optimized inference server exposing Whisper speech recognition, text-to-speech and LLM inference over REST, WebRTC and WebSocket APIs.toverainc
2026-08-27
2023-02-03
511 stars
445
tabbit-toy
A local OpenAI-compatible proxy that exposes Tabbit browser models to Cherry Studio and NextChat.goehou
2026-06-24
2026-06-23
510 stars
446
cordumai-orchestrationai-safetyautonomous-agents
Cordum is an out-of-process governance control plane for autonomous agents, offering policy enforcement, human approval gates, workflow scheduling, and signed audit trails.cordum-io
2026-08-26
2026-01-11
509 stars
447
termanyagent-terminalai-terminalterminal
Termany is an agent-native terminal for running many coding agent sessions in one window, with session management, diffs, ports, skills, and token-cost tracking.thinkany-ai
2026-11-06
2026-06-29
504 stars
448
teamclaudeanthropicclaudeclaude-code
A local multi-account proxy for Claude Code and Codex that pools subscriptions, API keys, and third-party backends, rotating accounts as quotas run out.KarpelesLab
2026-11-16
2026-03-24
502 stars
449
Agent-Cockpitai-agentsclaude-codecode-review
Agent Cockpit is a local whiteboard and MCP server for AI research agents that traces every claim back to the run and code that produced it, with staleness checks and replay.chutingyean
2026-11-14
2026-10-26
501 stars
450
dsh-codex-subscriptionchatgptcodexdeepseek-harness
This DSH plugin connects a ChatGPT or Codex subscription to DeepSeek Harness, adding subscription sign-in, Codex model selection, quota tracking, image generation, web search and optional phone-based remote control without an API key.WSL043
2026-11-17
2026-08-13
501 stars
451
OpenTagclaudeclaude-tagagent-gateway
A Slack-native agent gateway that routes team threads to Claude Code, Codex, OpenCode, Docker, or HTTP agents, adding approvals, audit logs, shared memory, and channel-level policy.linxidnju
2026-09-10
2026-06-27
500 stars