No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
Edition — August 16–31, 2026
6 standout picks across 14 categories. Backfilled per our research methodology: candidates sourced from Hacker News and GitHub within this fortnight's window, then checked against each product's own site or repository. Every pick carries a dated evidence link.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
VoiceMem
Universal memory for voice agents
Fully streaming universal memory layer for voice agents.
VoiceMem is memory infrastructure for voice agents that need persistent understanding of a user. Its streaming 'dual-brain' design stores factual information (schemas and entities) in a left brain and emotional and personality data in a right brain, aiming for accurate, personality-aware, low-latency and low-cost memory. It's Apache-2.0 and open source, built for developers shipping real-time voice applications.
Why it mattered
Universal, fully-streaming memory infrastructure built specifically for voice agents, targeting latency at the architecture level.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
Reverify
Grounded, hallucination-checked agent toolkit
Agents propose; deterministic tools decide, every claim checked.
Why it mattered
An MCP server + CLI that makes agents propose while deterministic tools decide, checking every claim against ground truth — a direct answer to hallucination in agent workflows.
Operator Memory
Self-improving context engine for coding agents
Self-improving context engine for coding agents.
Why it mattered
A self-improving context engine for coding agents — part of the fortnight's run of memory/context layers aimed at making coding agents learn across sessions.
TabTin
Humans + multiple AI agents, one workspace
Workspace where people and multiple AI agents collaborate.
Why it mattered
A shared workspace where people and multiple AI agents work together — an early take on multi-agent collaboration surfaces.
Runable
AI agent that builds and grows a business
Go-to-market agent: ads, social, SEO, customer acquisition.
Runable is an AI agent platform that lets non-technical founders build a website or app from natural-language prompts, then extends into go-to-market work — running ad campaigns, managing social media, handling SEO and optimizing presence in AI-chatbot results. It manages the underlying infrastructure (deployment, analytics) so users can turn AI-generated products into working businesses without stitching services together. In August 2026 it raised a $21M Series A (co-led by Susquehanna Venture Capital and Nexus Venture Partners) at a $65M post-money valuation.
Why it mattered
Pushes AI agents past building software into customer acquisition and growth — the go-to-market automation frontier — with a dated, reputably-reported Series A.
Tel-Agent
Open-source AI phone assistant
Self-hostable AI phone assistant, open source.
Why it mattered
An open-source AI phone assistant — part of the fortnight's crop of self-hostable voice and telephony agents.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.
No credible in-window candidate met the evidence bar for this category this edition — we flag it rather than force a weak pick.