Yann Bordelanne evaluated IBM Bob, IBM's AI coding assistant, against real-world IBM Maximo tasks including BIRT report maintenance, application XML configuration, Java library conflict troubleshootin…
A developer argues that large analytical SQL queries fail not because SQL is hard but because meaning is distributed across CTEs, joins, and derived metrics, and proposes semantic views as a compressi…
A developer behind DealMind described an architecture for an LLM-powered SaaS price negotiation tool that organizes memory, evidence, strategies, what-if analysis, counteroffer guidance, and learning …
AuraPunk is being built as an Agentic Development Environment (ADE) that organizes autonomous coding agents as first-class engineering work, using cards/SPECs to bind intent, execution, and evidence a…
The Apache Software Foundation ran full security scans across 230 of its repositories during a three-day window in August 2026, using Anthropic's Claude Mythos 5 through the Project Glasswing security…
Fullstack developer Taqui built Drawva, an open-source infinite-canvas whiteboard engine that uses a multimodal AI perception agent to interpret freehand sketches and convert them into live diagrams, …
The ERR.SYS / 0xRAGE404 team added a free-tier provider gate to their self-hosted agent swarm after noting that Meta's Contributor tier, at roughly $0.10 per million input tokens, may use prompts and …
A controlled study by Jiayi Chen and Guiling Wang at the New Jersey Institute of Technology found that paying for test-time reasoning in LLM trading agents produced no reliable improvement in net port…
A developer built RepoMind, an open-source, memory-powered code-review agent that learns and recalls team-specific engineering conventions using a persistent knowledge layer called Hindsight. The agen…
A developer built IncidentMind, an AI-powered incident investigation assistant that investigates software incidents, captures resolutions, and retains that experience in Hindsight memory to inform fut…
A Peking University paper (arXiv:2609.31430) by Zhensheng Zou, Guoqing Wang, and Dan Hao introduces Latent Observations, Hard Actions (LOHA) and Anchored Context Distillation (ACD), a context-compress…
A developer built a Python MCP server that exposes GitHub tools to any MCP client while delegating all OAuth handling to Nango, so the server code never sees a GitHub token and only holds a Nango secr…
A three-layer attribution framework published by Search Engine Land on September 21, 2026 argues that Google Analytics 4 alone undercounts answer engine optimization because AI-driven discovery often …
A developer built an AI incident response agent that uses Hindsight as a persistent memory layer, letting the agent recall relevant past incidents alongside current evidence during an investigation an…
A developer built Sanity Social, a social content operating system for agencies that runs as a Sanity App SDK application inside the Sanity Dashboard and manages the full lifecycle of social content —…
A developer's analysis of roughly 4,300 real coding-agent sessions (Claude Code and Codex, 43 developers, ~350,000 LLM steps) found that the median LLM step re-sends about 119,000 cached prefix tokens…
A developer at MVP studio Asper Brothers analyzed three cases of AI agents misbehaving on the web: OpenAI research agents that made roughly 13,000 edits on German UseMod wikis in a week while leaving …
A developer built SatQuery AI, a conversational system that lets users query satellite and Earth-observation imagery in natural language instead of translating questions into specialized geospatial op…
A developer built HealthBridgeApp, an Android app that reads Garmin biometric telemetry (overnight HRV RMSSD, sleep architecture, resting heart rate, SpO2, running pace) from the on-device Android Hea…
A developer built DealMind, a negotiation decision-support agent that uses the Hindsight long-term memory layer to recall an organization's past deal outcomes and turn them into evidence for recommend…