Trending

A benchmark for coding agents that tests whether they can formally verify properties of real-world Rust web apps in Lean 4. It includes upstream code, i5h ports, extracted Lean models, proof attempts, and task-by-task results.

Strata is a governed semantic layer and BI platform built for AI-safe analytics, with dashboards, agent-facing querying, and federated OLAP routing.

Open-source Rust LLM gateway for AI agents with full-fidelity traces, a tamper-evident audit ledger, offline verification, and in-request guardrails.

Paldron is a Go-based policy gate and sandboxed exec tool for coding-agent commands. It can allow, deny, or mark runs broken, supports Linux-focused isolation with Landlock/seccomp, and includes quickstart and policy examples.

Layout is an AI-powered ordering platform that lets assistants like ChatGPT and Claude place real food orders end to end. The site positions it as transactional infrastructure for restaurant ordering, with a developer platform, merchant tools, and a connector flow for assistants.

Self-hosted approval gateway for AI agent tool calls. It checks actions against rules, pauses risky ones for human approval, and keeps a tamper-evident audit trail. The repo shows setup, live demo flow, and integrations with Claude Code and MCP apps.

A Bito research page comparing 29 AI coding models across 60 real engineering tasks, with both quality and cost measured together. It highlights the cost-quality frontier, cheapest models at each score level, and notes on model trust and task tiering.

A macOS Electron app that lets you talk to Claude, Codex, and Grok side by side, with voice-driven control and a lightweight local setup.

AI-native application protection platform with autonomous LLM pentesting, proof-of-concept exploit findings, and a full API-driven workflow for scans, reporting, and remediation.

An unofficial Claude client for Nokia Series 40 phones, paired with a small Go server that handles TLS, chat backend access, and device pairing.

Open-source MCP-based relay for connecting a video game to AI agents, starting with World of Warcraft Classic Era. The repo describes the architecture, includes a self-host path, and splits components into SDK, WoW kit, platform, and bridge.

An MIT-licensed terminal coding agent for the Step ecosystem. It reads code, edits files, runs tests, supports MCP servers and plugins, and includes built-in static site publishing.

ContextIQ is a suite of AI engineering tools for inspecting context, agent workflows, protocol support, and payment or identity checks for AI systems. It includes inspectors for MCP/A2A/ARD, RAG chunking, traces, memory architecture, OIDC, DNS, x402, and ERC-8004.

Self-hosted voice agent runtime that streams speech-to-text, LLM output, and text-to-speech together in one process. The page shows quickstart commands, a minimal agent example, browser/client embedding, authentication notes, and performance benchmarks.

Self-hostable messaging workspace for AI agents and the people they work with. It positions agents as first-class members, with support for chat, email, and voice, plus Docker-based self-hosting and docs for getting started, CLI, and REST API.

An open-source tool that screens AI agent tool calls and tool results before they are used. It works as an MCP proxy plus hooks adapter, with policy-based decisions, shadow mode, and local logging.

Open-source code search for coding agents, built on Jev, with benchmarked speed and token-use gains across Codex, OpenCode, and Claude Code.

Ambits is a code-reading and search tool for AI agents that adds symbol-aware grep/rg output plus session history tracking so agents can remember what they already read after context compaction.

A benchmark page that aggregates public model lists from AI gateways into one matrix, showing which gateways offer each model and their per-million-token pricing.

Self-hosted AI agent for terminal and Telegram with Claude/Codex workers, live activity, and a deterministic permission kernel that gates every tool call.

A native bibliography manager for Omarchy that combines paper reading, note capture, and agent workflows with built-in MCP support.

Local AI memory observability and security tool for inspecting, auditing, and rolling back what agents remember about you.

A local-first developer tool that maps code changes back to the agent session that produced them, with transcript and tool-call citations for blame and debugging.

Local-first code review for worktrees created by agents, with support for staged, unstaged, and untracked changes before they become commits. It includes a desktop app, browser-based UI, MCP server integration, and machine-to-machine review flows over SSH, WSL, and Tailscale.