chromie.dev
the deterministic stack for web agents
chromie.dev launched on May 16, 2026.
What it does
chromie.dev employs deterministic tool calls for web agents: analyze past executions, build tailored tools around repeated actions, and invoke skills at runtime based on task and position. We use the model for the "why," but we enforce the "how" through deterministic skills. Don't risk the web agent reasoning through the DOM and making a costly mistake. Our skillset of self-healing tooling continually expands with automation flows seen, keeping us up to date and always growing.
Chromie helps government contractors qualify federal and SLED opportunities, simulate win strategies, and reach go/no-go decisions faster — with the team in the loop at every step.
Chromie gives government contractors one workspace to find, qualify, and pursue federal and SLED opportunities. It keeps your team in the loop — streamlining the operations around their judgment so go/no-go decisions arrive sooner and the firm can sustain a higher volume of applications. Chromie grounds your profile, documents, past performance, and team context into verified facts and knowledge pages. Every fit score, capture assessment, and draft reads from this Company Brain — not a static form. Chromie monitors SAM.gov and state, local, and education portals continuously and scores each solicitation against your profile rather than a keyword list. Every score carries its rationale, so…from chromie.dev
Does a similar job
all alternatives →
Notte Browser Agents2025 · notte.cc · ▲275Hey HN, We’ve been building browser agents for a while. In production, we kept converging on the same pattern: deterministic scripts for the happy path, agents only for edge cases. So we built Demonstrate Mode. The idea is simple: You perform your workflow once in a remote browser. Notte records the interactions and generates deterministic automation code. How it works: - Record clicks, inputs, navigations in a cloud browser - Compile them into deterministic code (no LLM at runtime) - Run and deploy on managed browser infrastructure Closest analog is Playwright codegen but: - Infrastructure…
- OHOne Human + One Agent = One Browser From Scratch in 20K LOCJan 2026 · emsh.cat · ▲324
Related: https://simonwillison.net/2026/Jan/27/one-human-one-agent-on...
Web Search Agents by NimbleAug 2026 · nimbleway.com · ▲371Self-learning agents automate web research + retrieval
Open-source browser for AI agentsMar 2026 · github.com · ▲155Hi HN, I forked chromium and built agent-browser-protocol (ABP) after noticing that most browser-agent failures aren’t really about the model misunderstanding the page. Instead, the problem is that the model is reasoning from a stale state. ABP is designed to keep the acting agent synchronized with the browser at every step. After each action (click, type, etc), it freezes JavaScript execution and rendering, then captures the resulting state. It also compiles the notable events that occurred during that action loop, such as navigation, file pickers, permission prompts, alerts, and downloads,…
Web-eval-agent – Let the coding agent debug itself2025 · github.com · ▲84Hey HN! We’ve been building an MCP server to help AI-assisted web app developers by using browser agents to test whether changes made by an AI inside an editor actually work. We've been testing it on scenarios like verifying new flows in a UI, or checking that sending a chat request triggers a response. The idea is to let your coding agent both code and evaluate if what it did was correct. Here’s a short demo with Cursor: https://www.youtube.com/watch?v=_AoQK-bwR0w When building apps, we found the hardest part of AI-assisted coding isn’t the coding—it’s tedious point-and-click…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com