301
The official implementation of Agent-as-a-Router for coding tasks, providing benchmark data, reference outputs, and gateway-level integration demos for backend model routing.lancezpf
2026-07-21
1.3k stars
Agent infrastructure
436 projects · page 4 / 5
301-400 of 436
302
CCManager is a CLI session manager for coding agents such as Claude Code, Gemini CLI, Codex, Cursor Agent, and OpenCode. It runs parallel sessions across Git worktrees and projects, with status tracking and restore.kbwo
2026-08-26
2025-06-07
1.3k stars
303
Agent Deck is a terminal control center for AI coding agents. One TUI manages Claude, Codex, OpenCode, and other CLI sessions with status detection, groups, forking, worktrees, MCP management, and cost tracking.asheshgoplani
2026-08-27
2025-12-03
1.3k stars
304
A large-scale realistic benchmark built from real-world vulnerabilities, including user-space and kernel cases, for evaluating AI agents' ability to develop working exploits.sunblaze-ucb
2026-07-23
2026-06-02
1.3k stars
305
A tmux sidebar for developers that shows live coding-agent state across sessions with quick switching, markers, and a local HTTP API.Ataraxy-Labs
2026-08-26
2026-03-19
1.2k stars
306
A hardware-focused vLLM fork for dual RTX 2080 Ti and other SM75 GPUs, with tuned launch profiles and validation for serving 27B- and 35B-class models locally.weicj
2026-08-25
2026-06-02
1.2k stars
307
An open-source governance layer for agent fleets with audit trails, deterministic replay, and compliance controls.sipyourdrink-ltd
2026-08-26
2026-03-22
1.2k stars
308
A desktop workbench for managing Pi and DSH coding-agent sessions across local projects.ayuayue
2026-08-03
2026-05-31
1.2k stars
309
llama.cpp fork focused on local LLM inference efficiency, using KVarN, KV-cache precision tailoring, and low-bit quantization to support longer context with better precision in the same VRAM.anbeeld
2026-07-19
2026-05-05
1.2k stars
310
A vim-style powerline statusline plugin for Claude Code that surfaces session usage, cost, context window, git state, and model details in the terminal.Owloops
2026-08-26
2025-08-10
1.2k stars
311
Endpoint visibility and security for AI agents with local detection, optional pre-action blocking and forensic reconstruction.perplexityai
2026-08-02
2026-07-24
1.2k stars
312
A self-hosted, multi-account gateway for Codex that exposes Responses and Chat Completions APIs with account grouping, client keys, usage tracking, and a management UI.zyycn
2026-10-18
2026-06-12
1.2k stars
313
ai-agent-skills is a universal installer and package manager for AI coding agent skills, shipping a curated library plus CLI tools to build and maintain your own skill collection.MoizIbnYousaf
2026-08-26
2025-12-17
1.2k stars
314
A read-only observability tool that turns Claude Code and Codex transcripts into a live flow graph of agents and tool calls, with replay, time travel and a local browser version.furkankly
2026-08-22
2026-08-18
1.2k stars
315
voxl is a low-latency Rust desktop streaming server that sends headless VM or sandbox screens to a browser over WebSocket, with screenshot and screen-wait APIs built for computer-use agents.tembo
2026-11-05
2026-06-18
1.1k stars
316
Sandboxed, ready-to-use Chrome browser images for browser automation and web agents, connectable via Playwright and Puppeteer.kernel
2026-08-26
2025-02-27
1.1k stars
317
Open-source sandbox infrastructure giving AI agents isolated virtual computers for code execution, browsing, and desktop use.celestoai
2026-08-16
2026-02-15
1.1k stars
318
An open evaluation platform and leaderboard for benchmarking long-term memory systems reproducibly.aml-memory
2026-08-12
2026-07-29
1.1k stars
319
Cisco AI Defense MCP Scanner scans MCP servers, tools, prompts, and resources for security threats using YARA, LLM analysis, and Cisco AI Defense, available as a CLI, SDK, and REST API.cisco-ai-defense
2026-08-26
2025-09-24
1.1k stars
320
CC Pocket is a mobile client for Codex and Claude that connects through a local Bridge Server to start, approve, and review coding-agent sessions remotely.K9i-0
2026-08-26
2026-02-06
1.1k stars
321
A local-first security layer for AI agents that reviews shell commands, file access, packages, plugins, and MCP calls before they run.hashgraph-online
2026-11-01
2026-03-28
1.1k stars
322
FizzGate is a Java API aggregation gateway offering API management, orchestration, masking, security, and tracing, plus an LLM gateway with multi-provider routing and MCP support.fizzgate
2026-08-26
2020-08-31
1.1k stars
323
A desktop app for running multiple AI coding agents in parallel, each isolated in its own git worktree with diff review.johannesjo
2026-08-11
2026-02-18
1.1k stars
324
Agentic Radar is an open-source CLI security scanner for agentic workflows. It visualizes agent graphs, inventories tools and MCP servers, maps findings to OWASP risks, and runs adversarial tests against agent systems.splx-ai
2026-08-26
2025-02-12
1.1k stars
325
FanBox is a desktop cockpit for coding agents: browse and preview local files on one side, run Claude Code or Codex in an embedded terminal on the other, and watch every change, diff and session.alchaincyf
2026-08-27
2026-06-10
1.1k stars
326
A local-first desktop manager and CLI that organizes AI agent skills centrally and syncs them across 32 coding tools via symlinks.jiweiyeah
2026-08-27
2026-02-06
1.1k stars
327
A serverless compute platform for AI agents, offering fast MicroVM sandboxes, durable filesystems, snapshots, and orchestration for running untrusted or LLM-generated code at scale.tensorlakeai
2026-10-08
2024-11-15
1k stars
328
A Windows utility that replaces the built-in prompts of DSH, WorkBuddy, ZCode and Codex clients with a custom persona, with backups, one-click restore and self-checks.z91772524-ai
2026-11-04
2026-09-17
1k stars
329
ThinkWatch Lite is a local gateway for Claude Code, Codex, and other AI clients that switches upstreams, redacts secrets, blocks dangerous tool calls, and traces usage.ThinkWatchProject
2026-10-04
2026-09-12
1k stars
330
MCPM is a CLI package manager and registry for Model Context Protocol servers, letting you search, install, profile, route, and connect MCP servers to Claude Desktop, Cursor, and other clients.pathintegral-institute
2026-08-27
2025-03-21
1k stars
331
Local-first CLI and web dashboard that reads Claude Code, Codex and Gemini CLI session logs to report token usage and cost by model, project and day.yakuikai
2026-10-13
2026-09-21
1k stars
332
A server-centric Git backend for coding agents with sparse fetch, server-side history, queue-free landing, changeset logs and scalable database storage nodes.feder-cr
2026-10-16
2026-10-15
1k stars
333
A self-hosted web command center for OpenCode that manages coding-agent sessions, git, terminals, and schedules from desktop or phone.chriswritescode-dev
2026-07-09
2025-11-24
1k stars
334
A fast Rust-powered statusline HUD for Claude Code that shows model, workspace, Git status, context usage, and rate limits. It installs via npm and configures Claude Code automatically.GaoSSR
2026-07-25
2026-06-26
995 stars
335
Maintains a fork of the llama.cpp local LLM inference engine, supporting low-bit model formats and multiple hardware backends for developers building local inference services.prismml-eng
2026-07-15
2026-02-25
994 stars
336
A commercial multi-model API gateway that proxies OpenAI, Claude, Gemini, and xAI endpoints behind OpenAI-compatible URLs, letting developers call LLMs without their own accounts.xing61
2026-08-27
2023-04-12
990 stars
337
An open-source self-hosted engine that runs coding agents inside isolated Docker sandboxes, each with a live preview URL and console.tastyeffectco
2026-08-27
2026-06-03
988 stars
338
A local proxy gateway that routes Claude Code requests to free or local models with routing, rate limiting, and Discord control.Rishurajgautam24
2026-08-27
2026-03-05
987 stars
339
An embedded SQLite reconciliation guardrail for AI-agent and worker runtimes that previews and closes stale task and delivery states after restarts without guessing success.MaxHu-xuan
2026-09-23
2026-08-23
982 stars
340
An OpenCode extension and profile manager that keeps portable, isolated configurations and installs editable agents, skills, commands, and registry components with update verification.kdcokenny
2026-09-15
2025-12-28
981 stars
341
A CLI proxy that routes Claude Code requests across providers with model routing, fallback, and format translation.samueltuyizere
2026-08-18
2026-04-17
979 stars
342
herdr-reviewr is a code-review pane for the herdr agent workspace that shows the agent's diff beside the chat, lets you comment on lines and sends the comments back to the agent.persiyanov
2026-10-03
2026-06-26
978 stars
343
Tracely is a self-hosted observability platform for AI agents, capturing traces, scoring responses, running regression tests, and enforcing CI gates so agent behavior stays stable across releases.jwuthri-cloud
2026-10-18
2026-10-11
978 stars
344
Local observability for AI coding agents, visualizing project activity and tasks via Map and Kitchen views.sodiumsun
2026-08-31
2026-08-21
978 stars
345
A desktop workspace for managing Pi, OMP, and Prime coding-agent sessions, terminals, and schedules.am-will
2026-08-26
2026-08-06
972 stars
346
Implements an OpenAI-compatible gateway by reverse-engineering ChatGPT web protocols, supporting account pool management, text and GPT-Image models, plus batch image generation and editing.yukkcat
2026-07-22
2026-05-27
971 stars
347
An API gateway that unifies reverse-engineered LLM libraries behind a standard OpenAI-compatible interface, with a web UI, load balancing, and channel management.RockChinQ
2026-08-27
2023-09-14
940 stars
348
A web UI and persistent runtime for the Pi Coding Agent, keeping sessions alive in real repos and letting you supervise them from any browser.jmfederico
2026-08-27
2026-05-07
935 stars
349
A terminal consciousness monitor for Hermes agents, visualizing memory, corrections, projects, and health in real time.joeynyc
2026-06-24
2026-03-31
934 stars
350
An enterprise-grade LLM API gateway that unifies 30+ model providers behind an OpenAI-compatible interface, adding token control, subscriptions, precise billing, clustering and an admin console.modelbus
2026-08-25
2026-07-24
932 stars
351
A scalable Windows benchmarking platform for evaluating multimodal desktop agents with reproducible OS environments.microsoft
2026-06-24
2024-07-29
915 stars
352
Scarf is a native macOS and iOS app for the Hermes AI agent. It provides dashboards, chat, session history, memory and skill editing, cron and MCP management over local or SSH connections.awizemann
2026-08-27
2026-03-31
914 stars
353
A macOS screen-recording tool that captures screen, narration and markup into a compact bundle of keyframes and transcripts, so coding agents can see a problem instead of reading a description.kitlangton
2026-10-20
2026-10-14
902 stars
354
A community benchmark evaluating AI agents on expert-curated, terminal-verifiable scientific research workflows.harbor-framework
2026-08-28
2026-01-25
894 stars
355
A management tool that deploys and safely reverses Claude Code instruction sets, with preview, apply and rollback plus a desktop beta.Jia-Ethan
2026-07-23
2026-06-29
884 stars
356
A real-time web cockpit for OpenClaw that manages agent fleets, sessions, kanban, voice, and usage observability.daggerhashimoto
2026-06-24
2026-02-19
874 stars
357
A self-hosted error tracking and observability platform that speaks the Sentry protocol and also ingests logs, transactions, release health, and AI-agent traces for monitoring applications and agent runs.rustrak
2026-10-04
2026-01-22
869 stars
358
A single-file inference program for running the full Kimi K3 model on consumer hardware, plus an OpenAI-compatible local API server for chat and coding agents.gavamedia
2026-07-31
2026-07-28
858 stars
359
An open-source runtime control sidecar for AI agents that masks sensitive data and blocks destructive SQL or HTTP commands on the wire, with risk analysis and human review, requiring only a port change.hoophq
2026-08-27
2022-08-29
842 stars
360
Cross-platform desktop notification companion for Claude Code, Codex, OpenCode, Gemini CLI, Cursor, and other coding agents, with sounds, click-to-focus, and webhook delivery.777genius
2026-09-10
2025-10-19
826 stars
361
A unified sim-and-real benchmark for generalist robot manipulation with tasks, simulation, and leaderboards.robodojo-benchmark
2026-08-02
2026-07-07
816 stars
362
A cross-platform desktop workspace for AI CLIs that unifies Claude Code and Codex terminal sessions, session history and diffs, token analytics, SSH remotes and Git worktree isolation.dark-hxx
2026-08-27
2026-03-12
815 stars
363
A local proxy and live terminal dashboard that intercepts LLM API traffic from Claude Code, Codex and similar CLIs to track token usage, context-window consumption, costs and archived prompts.jmuncor
2026-08-27
2026-01-27
811 stars
364
Version control for AI agents that logs every edit, blames lines on prompts and inspects any step.regent-vcs
2026-06-24
2026-04-30
808 stars
365
PasteGuard is a local-first privacy proxy for AI. It masks PII and secrets before requests reach ChatGPT, Claude, Gemini, Codex or other providers, and can be self-hosted.sgasser
2026-08-27
2026-01-08
805 stars
366
Heeler is a native iOS console for herdr. Over SSH it lists coding agents across your machines, opens their real terminals or chat, sends instructions, and pushes an alert when an agent needs you.ZingerLittleBee
2026-10-07
2026-07-18
804 stars
367
Local-first observability for AI coding agents. Agent Console tracks tokens, cache use, models, and cost across Claude Code and Codex sessions, with a self-hosted team hub and signed macOS builds.LockedinLabs-AI
2026-09-28
802 stars
368
OpenCode Studio is a local web GUI for managing OpenCode configuration. It lets users toggle MCP servers, edit skills and plugins, handle authentication, switch profiles, and review token usage without hand-editing JSON.Microck
2026-08-27
2025-12-29
796 stars
369
An open-source agent engineering platform for tracing, evaluating, monitoring and debugging AI agents, with a self-hosted dashboard and SDK integrations for LangGraph, CrewAI and more.chirpz-ai
2026-08-23
2025-12-16
795 stars
370
A macOS menu-bar app that supervises a local DeepSeek V4 server, manages model downloads, and launches coding agents.notatestuser
2026-08-14
2026-05-29
791 stars
371
A Pi extension that exposes Claude Code (via the Agent SDK) as a model provider inside Pi, forwarding tools and skills, with an optional AskClaude delegation tool.elidickinson
2026-08-20
2026-03-25
791 stars
372
A Go proxy that turns Google AI Studio's web playground and Build channels into OpenAI-, Anthropic-, and Gemini-compatible APIs. It supports multi-account routing, images, video, TTS, and a desktop management UI.Mag1cFall
2026-10-28
2025-08-21
789 stars
373
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
788 stars
374
Coi gives each AI coding agent its own isolated Linux system container with root, Docker and systemd. It keeps host credentials out, enforces network rules, monitors for threats, and pauses or kills dangerous sessions automatically.mensfeld
2026-09-29
2026-01-07
785 stars
375
Coi gives each AI coding agent its own isolated Linux system container with root, Docker and systemd. It keeps host credentials out, enforces network rules, monitors for threats, and pauses or kills dangerous sessions automatically.coipond
2026-09-30
2026-01-07
785 stars
376
A self-hosted Gemini web reverse proxy that exposes OpenAI-compatible and native Gemini APIs, plus MCP tools, an admin panel, cookie pools, and proxy rotation.zexadev
2026-11-03
2026-05-29
782 stars
377
Lightweight daemon and dashboard for tracking AI API quotas and spending across multiple providers locally.onllm-dev
2026-08-27
2026-02-06
772 stars
378
A local-first work ledger for coding agents that breaks tasks into steps, tools, files, tests, tokens, and estimated cost, separating reported outcomes from verified ones.mikehasa
2026-07-30
2026-07-24
755 stars
379
A self-hosted multi-device terminal server built for AI coding agents, with server-side session persistence, plugins, and panes for files, SSH, and previews so you can run Claude Code or Codex from any device.xichan96
2026-08-27
2026-05-12
738 stars
380
A native MLX speculative-decoding inference engine that speeds up local LLMs on Apple Silicon.arahim3
2026-08-20
2026-06-29
736 stars
381
A tiny macOS menu bar app that shows Claude Code's live status—thinking, running tools, awaiting permission, and elapsed time—aggregating multiple sessions at a glance.m1ckc3s
2026-08-27
2026-06-21
731 stars
382
A local gateway and control center for Codex Desktop managing providers, account pools, voice, routing, and session import.aitabby
2026-08-07
2026-05-29
730 stars
383
A mobile companion for Codex CLI that relays sessions to your phone for monitoring and steering.gronxb
2026-08-03
2026-04-27
728 stars
384
An inference engine built on stock llama.cpp that runs oversized MoE models on memory-constrained phones by streaming only routed experts from flash without quality loss.helldez
2026-07-17
2026-07-10
709 stars
385
A lightweight Windows taskbar widget that shows real-time usage limits and reset times for Claude Code, Codex, Cursor, Grok Build, Copilot, and other coding services.codezeno
2026-08-25
2026-02-26
695 stars
386
A visual conversation workspace plugin for DeepSeek Harness that maps sessions, follow-ups, and branches onto a draggable, zoomable canvas while keeping native sessions as the source of truth.liangmianya
2026-08-25
2026-08-16
694 stars
387
A terminal manager running multiple coding-agent CLIs side by side in persistent tmux sessions with status, prompts and diff review.YoanWai
2026-08-13
2026-07-15
682 stars
388
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
662 stars
389
ANOLISA is Alibaba's open-source Agentic OS stack that adds runtime management, context compression, memory, security isolation, and observability around existing AI agents.alibaba
2026-08-21
2026-03-30
662 stars
390
ANOLISA is a system software stack for AI agent workloads on Linux and macOS, adding context compression, persistent memory, skill delivery, workspace checkpoints, security policies, and observability.agentic-os-org
2026-09-12
2026-03-30
660 stars
391
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
655 stars
392
Native .NET inference engine for GGUF text and multimodal LLMs, providing a console app, web chatbot interface, and Ollama/OpenAI-compatible APIs with GPU support across Windows, macOS, and Linux.zhongkaifu
2026-07-25
2026-04-03
652 stars
393
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
394
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
649 stars
395
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
396
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
397
A self-hosted LLM gateway for AI coding tools that routes by complexity, compresses tool results, and caches semantically.Fast-Editor
2026-08-27
2025-12-03
640 stars
398
A desktop tray app that routes coding agents through a local proxy pipeline to compress prompts and cut token costs.gglucass
2026-08-27
2026-03-30
635 stars
399
A terminal multiplexer for AI coding agents that runs Claude Code, Codex, OpenCode, and others side by side in one tmux TUI with live status and diff review.wainmann
2026-11-03
2026-07-15
632 stars
400
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
616 stars