Small U.S. town, big company. Can it weather the tariff Blizzard? (Digi-Key)
24 by upofadown | 9 comments on Hacker News.
Sunday, 15 March 2026
Saturday, 14 March 2026
New top story on Hacker News: Show HN: GitAgent – An open standard that turns any Git repo into an AI agent
Show HN: GitAgent – An open standard that turns any Git repo into an AI agent
9 by sivasurend | 0 comments on Hacker News.
We built GitAgent because we kept seeing the same problem: every agent framework defines agents differently, and switching frameworks means rewriting everything. GitAgent is a spec that defines an AI agent as files in a git repo. Three core files — agent.yaml (config), SOUL.md (personality/instructions), and SKILL.md (capabilities) — and you get a portable agent definition that exports to Claude Code, OpenAI Agents SDK, CrewAI, Google ADK, LangChain, and others. What you get for free by being git-native: 1. Version control for agent behavior (roll back a bad prompt like you'd revert a bad commit) 2. Branching for environment promotion (dev → staging → main) 3. Human-in-the-loop via PRs (agent learns a skill → opens a branch → human reviews before merge) 4. Audit trail via git blame and git diff 5. Agent forking and remixing (fork a public agent, customize it, PR improvements back) 6. CI/CD with GitAgent validate in GitHub Actions The CLI lets you run any agent repo directly: npx @open-gitagent/gitagent run -r https://ift.tt/C2A1q0b -a claude The compliance layer is optional, but there if you need it — risk tiers, regulatory mappings (FINRA, SEC, SR 11-7), and audit reports via GitAgent audit. Spec is at https://gitagent.sh , code is on GitHub. Would love feedback on the schema design and what adapters people would want next.
9 by sivasurend | 0 comments on Hacker News.
We built GitAgent because we kept seeing the same problem: every agent framework defines agents differently, and switching frameworks means rewriting everything. GitAgent is a spec that defines an AI agent as files in a git repo. Three core files — agent.yaml (config), SOUL.md (personality/instructions), and SKILL.md (capabilities) — and you get a portable agent definition that exports to Claude Code, OpenAI Agents SDK, CrewAI, Google ADK, LangChain, and others. What you get for free by being git-native: 1. Version control for agent behavior (roll back a bad prompt like you'd revert a bad commit) 2. Branching for environment promotion (dev → staging → main) 3. Human-in-the-loop via PRs (agent learns a skill → opens a branch → human reviews before merge) 4. Audit trail via git blame and git diff 5. Agent forking and remixing (fork a public agent, customize it, PR improvements back) 6. CI/CD with GitAgent validate in GitHub Actions The CLI lets you run any agent repo directly: npx @open-gitagent/gitagent run -r https://ift.tt/C2A1q0b -a claude The compliance layer is optional, but there if you need it — risk tiers, regulatory mappings (FINRA, SEC, SR 11-7), and audit reports via GitAgent audit. Spec is at https://gitagent.sh , code is on GitHub. Would love feedback on the schema design and what adapters people would want next.
Thursday, 12 March 2026
New top story on Hacker News: Show HN: Detect any object in satellite imagery using a text prompt
Show HN: Detect any object in satellite imagery using a text prompt
8 by eyasu6464 | 1 comments on Hacker News.
I built a browser-based tool that uses Vision-Language Models (VLMs) to detect objects in satellite imagery via natural language prompts. Draw a polygon on the map, type what you want to find (e.g., "swimming pools," "oil tanks," "solar panels"), and the system scans tile-by-tile, projecting bounding boxes back onto the globe as GeoJSON. The pipeline: pick zoom level + prompt → slice map into mercantile tiles → feed each tile + prompt to VLM → create bounding boxes → project to WGS84 coordinates → render on map. No login required for the demo. Works well for distinct structures zero-shot; struggles with dense/occluded objects where narrow YOLO models still win.
8 by eyasu6464 | 1 comments on Hacker News.
I built a browser-based tool that uses Vision-Language Models (VLMs) to detect objects in satellite imagery via natural language prompts. Draw a polygon on the map, type what you want to find (e.g., "swimming pools," "oil tanks," "solar panels"), and the system scans tile-by-tile, projecting bounding boxes back onto the globe as GeoJSON. The pipeline: pick zoom level + prompt → slice map into mercantile tiles → feed each tile + prompt to VLM → create bounding boxes → project to WGS84 coordinates → render on map. No login required for the demo. Works well for distinct structures zero-shot; struggles with dense/occluded objects where narrow YOLO models still win.
Subscribe to:
Comments (Atom)