#agent

Orchestration spine for long-running pi development — pi-native batch orchestration with Taskplane-compatible task packets

一体化 AI 工作平台 SaaS

LLM agent evaluation framework with 7 Harness Gates (A–G) and 58 metrics. Supports LangChain, CrewAI, AutoGen, DSPy, PydanticAI. Native LLM-as-Judge, OTEL tracing, FastAPI dashboard.

AI-driven pi-like agent for cyber security — single binary for pentest, red team, bug bounty

An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay

TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.

Evi — local-first personal AI assistant (CLI + web + desktop) over local LLM backends

Own your agent. Run tasks, use wallets, and mine.

一个面向 AI Agent 的通知配置工具。支持将 Claude Code、Codex、Grok Build 等 Agent 的事件通知推送到飞书、企业微信、钉钉和系统通知。

Agentic engineering supersystem — one CLI to run the full /mavis-ship chain. Bundles 38 curated integrations + 1890 skills + the v2.7.1 arsenal (orchestrate.py + catalog.py + autopilot + mavis-ship-uni + big-boss persona). MIT.

Shrinks your AI agent's tool output so it burns fewer tokens, without changing what the agent reads. Lossless by default, no decode step.

a autonomous open-source coding tool

Agent-ergonomic CLI for task/backlog management with pluggable backends (markdown, sqlite, remote trackers)

A demarkus library FE reading room

Providing unified trait abstractions for AI models

The official Lombard SDK for Bitcoin staking and LBTC operations across Bitcoin, EVM, Solana, Sui, and Starknet.

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

Manage iCloud Hide My Email from your terminal. Create, search, and export aliases with commands, JSON scripts, or a coding agent.

Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP

Опис репозиторію не опубліковано.

Опис репозиторію не опубліковано.

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

Universal AI agent middleware. Gives CLI agents (Claude Code, Gemini CLI, Codex, OpenCode) 22+ messaging channels, persistent sessions, and 50 MCP tools. Fork of OpenClaw with the platform layer replaced by AgentRuntime.

AI-native, open-source Frame.io alternative for creative collaboration.

skcomms — sovereign realm-aware communication protocol + transports for AI agents (FQID addressing, BLE/LoRa mesh, glossa)

Turns a plain notes repo into a bridge: one repo that holds the plan and drives agentic work across your other repos.

LLM-driven browser automation with wallet extension testing. Accessibility tree + optional vision.

Open source coding agent forked from OpenCode.

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.