Autonomous AI agents that perform tasks independently
Zyntria Labs
Framework-neutral Python SDK for native Vintraa agents.
RISEN Lab
Schema definitions and utilities for the AgentLogs dataset
Claire Muwanguzi
Continuous, least-privilege authorization for multi-agent AI systems.
Optccopa
A model harness like claudecode or codex built in python, supports Anthropic natively and a large amount of models via OpenRouter and Ollama
...morePascalAI2024
Voice-first J.A.R.V.I.S. desk companion for the Waveshare ESP32-S3 Touch AMOLED 1.75C — Gemini Live, reactive round UI, physical privacy, motion, OTA, and policy-gated MCP tools.
...moreNicoGenti
Cost-aware multi-agent orchestrator kit for OpenCode CLI — one routing agent, 14 specialized subagents, zero application code touched by the router.
...moreqgeng1465
A wet-lab design assistant whose numbers are computed and re-proved, never guessed. Verifiable wet-lab experimental design: organ-on-chip geometry, fluidics, dosing and statistics that an LLM can reason over without hallucinating.
...moreandreihasna2
Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness
ssj4sunny
Cross-platform AI agent skill for UK legal research - legislation and case law from two public, unauthenticated sources. Installs into Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf, and 30+ other agents.
...moreyottameta
Cross-session / cross-project workflow standard for all AI agents: read the state on start, store state nearby in a unified .workflow directory, persist logs/tasks/decisions while working, and leave a self-contained handoff anchor on finish. Triggers when
...moreyytbit
Multi-agent dashboard skill for DeepSeek Harness -- status reports, task tracking, progress visualization
GitHub Actions
A permission gate for Pi in the style of Claude Code's auto mode
jeremyguo
Use one shared Playwright browser together with your DeepSeek Harness AI.
AnsysEM Agent Bridge contributors
Unofficial local-first agent bridge for Ansys Electronics Desktop
CrowdDrop's SDK for embodied-agent hardware. This release covers cloud_brain: the LLM stays in the cloud, the device is a thin actuator/sensor bridge over Pub/Sub.
...moreCLI for folder assurance checks — coverage, staleness, and baselines.
HopkeyEZ
An extensible multi-agent framework: tool-calling loop, sub-agents, cross-session memory, and a unified multi-model protocol layer — register your own tools to embed AI agents into any app. First shipped as an autonomous coding IDE. Supports OpenAI and Anthropic.
...moreOMD-123
Protect AI agents from runaway loops, repeated tool calls, and uncontrolled execution. Provider-independent, zero-dependency, TypeScript-first.
...morejunnhwan
面向长视频内容理解的RAG知识库问答平台
cdavid817
《企业级 Agent 从入门到专家（2026版）》——从单 Agent 核心机制到多 Agent 与企业落地的工程化实战教程，配套可运行贯穿项目与 CI 验证门禁。
kasparovabi
An unofficial native macOS (SwiftUI) client for dsh, the DeepSeek agent harness — sessions, live trajectory, tool approvals, models, goals, subagents.
...moreLyleMi
DeepSeek Harness AgentFactory provider for the official Codex App Server
Adversarial multi-agent adjudication for structured decisions
kap10
A minimal, zero-API CLI that guides developers through building software with any AI by giving them the right prompt at each step.
...more