Search
dsh-agent-team-presets
bloodarea
Reusable Agent Team presets for DeepSeek Harness: a captain plus members with their own prompt, model, reasoning effort, and tools.
...more@ariponly/nanoai
ariponly
NanoAI — a personal AI agent on your own machine: terminal chat, gateway API with live streaming, and a workspace where it reads, writes, and organizes files for you.
...morelitmus-agent-toolkit-darwin-arm64
amine-amaach
Temporary package placeholder for staged publishing
litmus-agent-toolkit-darwin-x64
amine-amaach
Temporary package placeholder for staged publishing
litmus-agent-toolkit-linux-arm64
amine-amaach
Temporary package placeholder for staged publishing
litmus-agent-toolkit-win32-x64
amine-amaach
Temporary package placeholder for staged publishing
litmus-agent-toolkit
amine-amaach
Temporary package placeholder for staged publishing
litmus-agent-toolkit-linux-x64
amine-amaach
```bash npm install -g litmus-agent-toolkit litmus --help ```
KnowAgenticRAG
Zhongye1
基于Fastapi + React 实现的面向智能知识管理的Agentic RAG系统,支持私有部署和多租户,以及知识图谱、多智能体、MCP/Skills、沙盒与权限管理等功能。
agent-evidence-observer
Sankalp Gilda
Record brokered agent writes and check selected native reports offline
backstage-agents
Khal
Backstage Agents SDK — conversas, custo e eventos de agentes Python para o Backstage
agent-evidence-vocabulary
Sankalp Gilda
Versioned terms for claims about agent execution evidence
Moondream: Moondream 3 Preview
moondream
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
...moreMoondream: Moondream 3.1
moondream
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
...morepixelagent
Pixeltable, Inc.
A Pixeltable-native agent framework for OpenAI, Anthropic, AWS Bedrock and Google Gemini
tapediff
thetsiklauri
Snapshot testing for AI agents: record, replay, and diff LLM traffic.
cloudpin
GitHub Actions
A seatbelt for your cloud CLIs: stops you, or your AI agent, from running commands on the wrong account.
openwop-client
openwop spec working group
Python SDK for OpenWOP, the open-source protocol for multi-agent workflow orchestration: run AI agents as workflows you can watch, pause for human approval and replay, on any host that implements it.
...morecedrodb
Luis Tavarez
Native Rust storage for agent checkpoints, hybrid memory retrieval and persistent local jobs
pbt-extra-model-kinds
Extra pbt model kinds: python_modal, agent_modal and agent37.