Dhenara Agent DSL– Framework for Complex Agents with Free Observability
Dhenara Agent DSL (DAD), an open-source framework for building, running, and managing AI agents! GitHub: https://github.com/dhenara/dhenara-agent Documentation: https://docs.dhenara.com/dhenara-agent/introduction Key Features: - Agent Lifecycle Management: Create, run, resume, and manage agents - Run Controls: Resume execution from any point to save on API costs - Built-in Observability: OpenTelemetry tracing with Jaeger and Zipkin support - Event System: Fine-grained flow control - Open Development: Build using standard tools (Git, VS Code) - No…
What it does
In the maker’s words, at launch
Dhenara Agent DSL (DAD), an open-source framework for building, running, and managing AI agents! GitHub: https://github.com/dhenara/dhenara-agent Documentation: https://docs.dhenara.com/dhenara-agent/introduction Key Features: - Agent Lifecycle Management: Create, run, resume, and manage agents - Run Controls: Resume execution from any point to save on API costs - Built-in Observability: OpenTelemetry tracing with Jaeger and Zipkin support - Event System: Fine-grained flow control - Open Development: Build using standard tools (Git, VS Code) - No Platform Lock-in: Build powerful command-line agents similar to Claude Code using just Git and VS Code Simple Architecture: DAD uses three main components: 1. Nodes: Basic execution units (API calls, file operations) 2. Flows: Collections of nodes with execution logic 3. Agents: High-level coordinators Sample: outer_loop_flow = FlowDefinition() # Outer loop outer_loop_flow.for_each( id="category_processor", statement=ObjectTemplate(expression="$expr{$hier{categories}.outcome.structured.categories}"), item_var="category", index_var="category_index", max_iterations=10, body=FlowDefinition().for_each( # Inner loop id="item_processor", statement=ObjectTemplate(expression="$expr{category.items}"), item_var="item", index_var="item_index", max_iterations=20, body=item_processing_flow ) ) While still in alpha, we've designed it to handle complex agent behaviors with robust control flow. We're Working On: - Budget control with pause/resume capabilities - Additional node types and integrations - Parallel execution for complex workflows - Enhanced visualization tools Try it out: `pip install dhenara-agent` We welcome your feedback on what would make this more useful for your AI agent projects! Thanks.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
