Newly Accepted

Open-source platform for governing AI usage across an organization, with MCP gateways, LLM gateways, hosted MCP servers, audit logs, and Claude Environments on Kubernetes.

A Rust terminal UI for running multiple Claude or Codex sessions in parallel, each tied to its own git worktree, issue, and pull request. It is built for developers juggling many tickets across GitHub, Jira, Linear, or local files.

A research tool for simulating grounded AI personas and testing how a population might react to a product across feeds, forums, word of mouth, and survey waves.

CTGT’s research post shows how deterministic LLM serving can still produce inconsistent pipeline outcomes, and introduces Concordance, an Apache 2.0 instrument for tracing where AI workflows diverge. The page includes the problem setup, benchmark details, findings, limitations, and a linked repo for reproduction.

An open-source coding agent that aims to use fewer tokens and less memory while supporting multiple models, browser automation, subagents, and MCP plugins.

A GitHub Blog case study showing how three Java Champions use GitHub Copilot to speed up development while keeping human review in the loop.

An interactive map of AI companies, models, products, people, hardware, and ideas that are drawing attention across English-language news and developer communities over the last 7 days.

A design write-up and product page for AgentTerm, a terminal-based AI workspace focused on steering agents, reviewing code, opening documents in-window, and coordinating work across desktop and devices.

CLI tool for archiving Claude Code, Codex, and Cursor sessions to S3 or R2, with session handoff, browsing, stats, and multi-machine continuity.

A live evidence-based lookup and audit service for MCP servers. It checks public health and ownership signals, returns PASS/REVIEW/BLOCK/UNKNOWN, and offers both REST and MCP access for agents.

A detailed benchmark-style article comparing Claude Code’s single-agent and multi-agent /code-review modes on hard pull requests, with measured cost, latency, and issue-detection results, plus a comparison to Quickchat Review.

A news and resource platform that ranks reporting by topic and relevance, adds AI summaries with source visibility, and includes a twice-daily news podcast.

Skillsync is a macOS app and CLI that searches past AI coding sessions across tools like Claude Code, Codex, Cursor, OpenCode, and Amp, then surfaces relevant recollections back into the current prompt. It’s positioned as private-by-default, with workspace sharing and agent-specific skill libraries.

A pure Go CLI and local API proxy for connecting apps and coding agents to DeepSeek R1/V3 through a web account, with OpenAI, Anthropic, and Ollama-compatible endpoints.

LayerFS is an open-source filesystem built for AI coding agents. It gives each tool call a writable workspace over shared history, with branching, checkpoints, and commit-based coordination for multi-agent workflows.

A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.

Founden is an autonomous software builder that turns a described idea into a live product with built-in site, app, database, payments, email, analytics, sign-in, automations, and back office. The page shows example products, ongoing autopilot behavior, and a Mac desktop app tied to existing model providers.

Sell-side broker for company data aimed at AI labs. The page explains valuation, buyer matching, deal flow, and publishes public pricing and buyer information for several data types.

An iPhone app that listens to a song, identifies the track, and estimates whether it was made by AI, returning Human, Unsure, or AI verdicts.

Maali is a privacy-first personal finance app for Mac and Windows with a local AI analyst that runs on your own computer. It imports bank statements or connects through SimpleFIN, categorizes transactions, surfaces spending insights, tracks net worth, and includes retirement planning.

A dated research report from Vouch that analyzes the MCP registry at scale, including corpus growth, transport split, credential classes, schema quality, and unreachable servers. It also points to queryable live data and the methodology behind the counts.

A benchmark for testing whether coding agents can show staff-level engineering judgment, not just produce correct code.

arXiv paper on Javo, a sales agent trained on commercial conversations and evaluated through public benchmarks plus a randomized field trial across 100 live websites.

Open-source, self-hosted analytics for MCP servers with dashboards for tool calls, latency, failures, client usage, releases, and exports.