agent — independent software & tools
-
context-optimizer
Reduce Claude token consumption by using local manifests to index and summarize project files for efficient context management.
-
mcp-remote
The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
-
aex
Open managed agent platform
-
claude-code-from-scratch
Build Claude Code from scratch with a step-by-step tutorial in TypeScript and Python for learning agent coding tools
-
fak
fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.
-
argus-agent
A harness that makes a small (or modest) LLM reliably run multi-step agentic tasks — tools, skills, memory, scheduling.
-
ai-badger
Source-of-truth marketplace + project scaffolder for custom Claude/agent skills, personas, and instructions. Organized as {stack|common}/{feature}; welcome-ai-badger scaffolds a repo, feed-badger contributes back.
-
nova-code
The coding agent purpose-built for DeepSeek — 95%+ cache hits · OS-sandboxed · tool-complete · install-and-go. 为 DeepSeek 量身打造的编程代理 — 95%+ 缓存命中 · OS 级沙箱 · 工具齐全 · 开箱即用
-
invinoveritas
The verification layer for autonomous agents — an independent, capital-aware verdict before an irreversible action (/review), a cryptographically signed proof after, and a public on-chain track record, losses included. Free EdgeProof backtest validation. Underneath: memory, sandboxed execution, marketplace. Pay in sats, USDC (x402), or card.
-
codex-dsh-subagent
Run ordinary DeepSeek Harness sessions as Codex-delegated agents over MCP
-
agenticloop
Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work
-
design-system-skill
-
cetridr
Rule the deep — a single-window command center for DeepSeek Harness agents
-
rune
🔮 Universal TTY ↔ AI Agent bridge and Ruby CLI framework
-
berimor
Детерминированная агентная архитектура: спецификации, ADR, roadmap и скелет реализации (Rust + TypeScript bootstrap)
-
Fintz-harness-kit
Project-agnostic AI agent harness kit with stage machine, loops, memory, and metrics dashboard.
-
agent-cli
A local-first, terminal-native agent harness: typed tools behind one fail-closed policy gate, append-only evidence, verified outcomes, and honest limits.
-
open-compute
Model-agnostic computer-use core: one agent loop for Claude, OpenAI CUA, and a mock backend — normalized coordinates, canonical action schema, central safety gate.
-
workbench-cli
A terminal workbench for running multiple coding agents side by side — tmux-backed, fast, remotely over SSH.
-
porcelain
Where agent work becomes trusted work. A review companion agents actually connect to: they publish a feature as a story, you comment, they resolve. Mac or any browser.
-
agentgate
ai security cli developer-tools agent firewall policy-as-code python anthropic claude-code
-
core-agent
Reusable Go base agent on the Google ADK — multi-provider (Gemini, Vertex, Claude on Anthropic + Vertex), MCP-native, with AGENTS.md, skills, and permissions wired up.
-
gridwork
Terminal-native agent OS. One binary: gw.
-
claude-context-vault
2026 AI Task Manager with Persistent Backlog & Multi-Machine Sync — Trove-Inspired
-
herdr-sandbox
Windows-native counterpart to a dev container.
-
cc-skills
Build reusable AI agent skills for marketing and engineering tasks with on-demand, domain-specific guidance.
-
Symbio
Symbio is an innovative project designed to empower users through seamless interaction with their machines. This flexible system adapts to commands, continually learning and evolving based on user input.
-
StratumCode
AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.
-
get-fable
Make the model you already use work more like a frontier model with better planning, persistent context, skills, hooks, failure handling, and verification
-
noeta
The server-side runtime for AI agents. Durable & crash-safe (event-sourced), multi-worker scheduling, per-session sandboxing, human-in-the-loop, provider-neutral. Host agents like Claude Code on your own infra — self-hostable, no vendor lock-in.
-
JanexAgent
The agent that grows with you 330+ SKILLS
-
antigravity-cli-hud
A production-grade, highly responsive terminal HUD for the Antigravity CLI. It dynamically monitors your agent state, token context, quota buckets, and active subagents in real-time.
-
s-loop
AI Desktop Workbench — chat, agent orchestration, scheduled tasks, desktop pet, all in one Tauri 2 app
-
thinkrail
Vibe code with pi in a lightweight, real IDE - The Vibe You Need
-
quireink
A self-hosted blog platform an AI agent can run for you. One Bun process, two SQLite files, no cloud account anywhere in the path.
-
quireink
A self-hosted blog platform an AI agent can run for you. One Bun process, two SQLite files, no cloud account anywhere in the path.
-
linkedin-outreach-agent
Self-hosted, agent-driven LinkedIn outreach framework. Agentic control loop exposed over MCP, real headful browser per account, safety state machine as a first-class subsystem. Apache-2.0.
-
EJAgent
EJAgent Core is an agent harness core with runtime control, extensibility, tool safety, context management, durable sessions, branching, and observability.
-
arc
A high-performance, lightweight agentic coding assistant for VS Code.
-
kition
Markdown documents,Data Tables, AI agents, browser research, and visual workflows.
-
wigolo
The go-to web for your agent!
-
a2wave
Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.
-
LMcode-cli
A terminal-native AI coding agent — a fast, scriptable TUI CLI for builders.
-
m365-copilot-companion-mcp
Personal-use MCP server that gives Microsoft 365 Copilot real hands on your own laptop: files, Python, Office, SQL, Web. 100+ tools, autonomous relay, easily extensible, no extra licences.
-
dsh-task-center
Task lifecycle plugin suite for DeepSeek Harness (dsh): agents claim work across sessions, wake up on schedule, quota-aware; idle/imported chats auto-mined into board candidates; full web kanban. | dsh 任务全生命周期插件族:跨会话认领、定时唤醒、额度感知、闲置会话自动抽取候选,配 Web 看板。
-
open-max
Minimal Rust terminal harness for coding. Small, extremely fast, and self-extensible.
-
coding-agent-free
Interactive AI coding agent using free OpenRouter models with real tool calling
-
agenterm
agent-term is the terminal for your agents' tree with communication like *mux
-
agenterm
AgenTerm is a software for your terminal agents work like *mux but more features. 面向多智能体协同工作的工具，强调人类用户作为"政委"提供决策意志，而工具本身则负责将这些意图转化为可执行、可观察的控制流程。它针对现有工具在多任务协同时易出现的上下文丢失、进程失控等问题，提出轻资源占用但重控制力的设计理念，支持终端、应用、资源集群等统一管理。该工具在智能政治论框架下运作，主张通过强化控制力来实现与自由意志的协同进化，而非单纯限制自由。
-
mexc-agent-trading-skills
MEXC crypto trading tools for Claude Code and OpenAI Codex, based on official MEXC API , with support for spot trading, futures trading, getting information about account, REST API, and WebSockets.
-
anywhere-agents
Manage agent configurations across projects with a single AGENTS.md file to standardize rules, skills, and permissions for any LLM-powered tool.
-
origin-memorycore
LLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold
-
starfleetctl
multi agent coordination / command & control toolkit following the Startrek fleet metaphor
-
mcp-gateway-orchestrator
Enterprise AI Guardrails 2026 🛡️ - MCP Security & Orchestration Toolkit
-
scratchpad
CLI to organize temporary agent knowledge into scratchpads, with a read-only visual viewer.
-
agentback
AI native API/MCP framework for the agent era. Built with agents, for agents.
-
LitosAiCodingAgent
Litos is a real AI coding agent written entirely in C#/.NET, no black box.
-
no_human
From ticket to reviewed pull request. Free and open-source, on your machine.
-
myAIspecials
ais
-
app
One Works application monorepo for AI agents, plugins, desktop, web, CLI, and Relay.