Search

AI-native version control for agentic workflows — structured checkpoints, spec-driven development, and multi-agent coordination

Spawn isolated AI agents in Docker containers

Silent watcher for LangGraph multiagent pipelines — detects silent failures, captures full state, enables step-level replay.

Long-term semantic memory plugin for Strands Agents backed by Amazon S3 Vectors

Lightweight AI agent orchestration framework

Core models and schemas for LlamaDeploy

Application server components for LlamaDeploy

LlamaAgents x Bedrock AgentCore deployment utilities

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verifi

Deterministic Observability Framework — formal governance, privacy benchmarks, and adversarial testing for multi-agent LLM systems

Generic LLM/RAG platform framework

AI model: Sathman/Meditation-Agent-SmolLM3-3B-v2-GGUF

AI model: rajat0910/telecom-knowledge-agent-gguf

AI model: screenpipe/pipe-agent-v6-GGUF

AI model: agentscope-ai/CoPaw-Flash-9B

AI model: agentscope-ai/CoPaw-Flash-2B-Q4_K_M

AI model: JFernandoGRE/testing_mcprl

AI model: golf-mcp/golf-prompt-guard

AI model: yueqis/full_sft_mcp_10k-qwen-7b-30k-5e-5

AI model: yueqis/full_sft_mcp_1k-qwen-7b-30k-5e-5