a personal assistant that lives on your machine, not someone else's cloud.
qwenpaw runs on your own hardware or in the cloud, remembers across chats, plugs into dingtalk, telegram and the rest, and keeps your data where you put it.
agentscope-ai/QwenPaw
1 like · 81 views
I built OptMem plugin for Hermes. It's one of the 24 in the official catalog.
Zero dependencies. No database, no embeddings, no API key.
An append-only log: summaries keep context small, the raw record is never deleted. OptMem from @VictorTaelin
rarf/optmem-hermes-plugin
2 likes · 1 repost · 297 views
Agents forget.
ReMe gives them a local Markdown knowledge base they can read, edit, and search - users keep the files, agents share the workspace.
Requires Python and a directory to write to.
agentscope-ai/ReMe t.co
6 views
💡 [Open Source Alternative to Paid Tools] QwenPaw: The Free Tool Taking Over GitHub! #shorts
Discover agentscope-ai/QwenPaw: Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
💬 Comment "QWENPAW" below for the direct link, or grab it from the links below:
👉 Interactive Star History & Live Analysis:
githubrepo.cloud
⭐ Embed Live Verified Badges in your README:
githubrepo.cloud
🔗 Direct GitHub Repository:
agentscope-ai/QwenPaw
📊 Repository Specs:
⭐ Stars: 35,554
🍴 Forks: 3,168
💻 Language: TypeScript
📜 License: Apache-2.0
#shorts #qwenpaw #agent #agentharness #agentscope #aiagent #ai #artificialintelligence #machinelearning
1 like · 44 views
AgentScope Java: Build distributed, production-grade, long-running agents (6.0k stars)
What it does
All text below is quoted directly from the project README.
>AgentScope Java 2.0 is a production-ready framework for building distributed, enterprise-grade agents, providing essential abstractions that work with rising model capability and built-in support for long-running, safely-controlled agent execution.
What is AgentScope Java 2.0?
- Event System: A unified event stream with 32 typed events for real-time frontend rendering and human-in-the-loop.
- Permission System: Tool-call gating: allow / require user approval / deny.
- Middleware: AOP-style hook interception for flexibly extending the reasoning-acting loop.
- Workspace & Sandbox: Run tools in isolated environments: local, Docker, Kubernetes, or AgentRun cloud sandbox.
- Multi-Agent Orchestration: Multiple subagent definition patterns with agent_spawn / agent_send and real-time event forwarding.
- Distributed Deployment: True distributed session and memory management (Redis / MySQL / PostgreSQL / OSS / COS) with cross-replica session recovery.
- Agent Evolution: Provides Agent observability and auditing, Agent evaluation and experimentation, and Agent asset management and continuous optimization.
>AgentScope Java requires JDK 17 or higher.
>Model providers are shipped as separate extension modules in 2.0. Add the one you need, for example, DashScope.
>Configure a shared Builder at startup, then use builder.build() to create and close an Agent for each request. The same identity and persistent storage keep the conversation across instances.
Repository
agentscope-ai/agentscope-java
Repository stats
|Metric|Value|
|:-|:-|
|Stars|5,979|
|Forks|1.5k|
|Last release|v2.0.4 (2026-10-08)|
|Languages|Java 76.5%, Go 14.2%, TypeScript 7.7%|
|Contributors|212|
|AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude (9 commits), Copilot (8), cursoragent (3)|
|AI co-authored commits|Claude: 9, Copilot: 9, Cursor: 3|
Main contributor
|Field|Value|
|:-|:-|
|Name|Albumen Kevin|
|GitHub|@AlbumenJ|
|Commits to this repo|182 (top contributor)|
|Bio|Apache Dubbo PMC|
|Company / Location|Earth|
|Followers|338|
2 points
AgentScope is an open source Python framework for building and running LLM agent apps. It pairs a reasoning-and-acting agent with a set of tools, a model layer, and an optional way to run it as a service. See the code at agentscope-ai/agentscope t.co
1 like · 7 views
AI 助理都像样，就是聊三天就失忆。
QwenPaw：自托管的个人 AI 助理
· 三层记忆，聊天沉淀成可检索的知识库
· 微信/QQ/钉钉/飞书都能直接喊它
· 自带本地小模型，免 API Key，数据不出机器
7 个多月 3.5 万星，Apache-2.0 协议
agentscope-ai/QwenPaw
#AI助手 #自托管 #MCP t.co
29 views
Mentions
a personal assistant that lives on your machine, not someone else's cloud. qwenpaw runs on your own hardware or in the cloud, remembers across chats, plugs into dingtalk, telegram and the rest, and keeps your data where you put it. agentscope-ai/QwenPaw
I built OptMem plugin for Hermes. It's one of the 24 in the official catalog. Zero dependencies. No database, no embeddings, no API key. An append-only log: summaries keep context small, the raw record is never deleted. OptMem from @VictorTaelin rarf/optmem-hermes-plugin
Agents forget. ReMe gives them a local Markdown knowledge base they can read, edit, and search - users keep the files, agents share the workspace. Requires Python and a directory to write to. agentscope-ai/ReMe t.co
💡 [Open Source Alternative to Paid Tools] QwenPaw: The Free Tool Taking Over GitHub! #shorts Discover agentscope-ai/QwenPaw: Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. 💬 Comment "QWENPAW" below for the direct link, or grab it from the links below: 👉 Interactive Star History & Live Analysis: githubrepo.cloud ⭐ Embed Live Verified Badges in your README: githubrepo.cloud 🔗 Direct GitHub Repository: agentscope-ai/QwenPaw 📊 Repository Specs: ⭐ Stars: 35,554 🍴 Forks: 3,168 💻 Language: TypeScript 📜 License: Apache-2.0 #shorts #qwenpaw #agent #agentharness #agentscope #aiagent #ai #artificialintelligence #machinelearning
AgentScope Java: Build distributed, production-grade, long-running agents (6.0k stars) What it does All text below is quoted directly from the project README. >AgentScope Java 2.0 is a production-ready framework for building distributed, enterprise-grade agents, providing essential abstractions that work with rising model capability and built-in support for long-running, safely-controlled agent execution. What is AgentScope Java 2.0? - Event System: A unified event stream with 32 typed events for real-time frontend rendering and human-in-the-loop. - Permission System: Tool-call gating: allow / require user approval / deny. - Middleware: AOP-style hook interception for flexibly extending the reasoning-acting loop. - Workspace & Sandbox: Run tools in isolated environments: local, Docker, Kubernetes, or AgentRun cloud sandbox. - Multi-Agent Orchestration: Multiple subagent definition patterns with agent_spawn / agent_send and real-time event forwarding. - Distributed Deployment: True distributed session and memory management (Redis / MySQL / PostgreSQL / OSS / COS) with cross-replica session recovery. - Agent Evolution: Provides Agent observability and auditing, Agent evaluation and experimentation, and Agent asset management and continuous optimization. >AgentScope Java requires JDK 17 or higher. >Model providers are shipped as separate extension modules in 2.0. Add the one you need, for example, DashScope. >Configure a shared Builder at startup, then use builder.build() to create and close an Agent for each request. The same identity and persistent storage keep the conversation across instances. Repository agentscope-ai/agentscope-java Repository stats |Metric|Value| |:-|:-| |Stars|5,979| |Forks|1.5k| |Last release|v2.0.4 (2026-10-08)| |Languages|Java 76.5%, Go 14.2%, TypeScript 7.7%| |Contributors|212| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude (9 commits), Copilot (8), cursoragent (3)| |AI co-authored commits|Claude: 9, Copilot: 9, Cursor: 3| Main contributor |Field|Value| |:-|:-| |Name|Albumen Kevin| |GitHub|@AlbumenJ| |Commits to this repo|182 (top contributor)| |Bio|Apache Dubbo PMC| |Company / Location|Earth| |Followers|338|
AgentScope is an open source Python framework for building and running LLM agent apps. It pairs a reasoning-and-acting agent with a set of tools, a model layer, and an optional way to run it as a service. See the code at agentscope-ai/agentscope t.co
AI 助理都像样，就是聊三天就失忆。 QwenPaw：自托管的个人 AI 助理 · 三层记忆，聊天沉淀成可检索的知识库 · 微信/QQ/钉钉/飞书都能直接喊它 · 自带本地小模型，免 API Key，数据不出机器 7 个多月 3.5 万星，Apache-2.0 协议 agentscope-ai/QwenPaw #AI助手 #自托管 #MCP t.co