Trending

A job board focused on AI engineering roles, with first-party listings for RAG, agents, evals, inference, and MCP-related work. The page shows live filters, location and seniority breakdowns, and a nightly refreshed feed of open roles.

Minimal LLM post-training experiments on a single 8GB GPU, covering SFT, DPO, and GRPO with a focus on forgetting, seed variance, and RL behavior.

A Linux-only CLI wrapper that lets users switch between isolated Claude Code accounts without re-authenticating, using separate config directories per profile.

A GitHub repository that provides an agent skill for rewriting documentation in ASD-STE100 Simplified Technical English, with install steps, examples, and support for multiple AI tools.

SHIP is an agentic engineering platform that assigns issues to specialist AI agents to plan, build, review, deploy, and test software on your own infrastructure. The page shows issue-to-PR workflow, mission timelines, cost tracking, model selection, and support for GitHub and Linear.

Wallfacer is an open-source terminal session manager for Claude Code. It indexes AI coding sessions into a local SQLite database so users can search, tag, group, resume, or delete sessions from both a TUI and CLI.

Sightmap is an open YAML format and CLI for maintaining shared runtime context about a web app for AI agents. The repo includes the spec, reference Go implementation, docs, and agent skills for browser use and authoring.

Heddle is a GitHub repository for a git-native coordination layer for coding agents, using intent leases, isolated worktrees, and gated landings to avoid agents overwriting each other.

Orchard is a managed backend for AI coding agents, letting users describe an app and have an agent connect database, auth, storage, email, analytics, and deployment services without cloud accounts or API keys.

Hotcell is a self-hostable sandbox SDK for AI agents that runs isolated sandboxes on local hardware or servers. The page shows setup, CLI commands, key handling, egress control, and support for containers or microVMs.

Browser automation CLI for AI agents with anti-bot handling, human takeover, parallel multi-session browsing, and isolated multi-account workflows.

Projektor is a self-hosted issue tracker and wiki built for AI agents as the primary client, with MCP-based agent access and Cloudflare-based deployment.

Open-source security research tool for auditing Python AI agents and codebases with AST analysis and Docker-based runtime verification.

A local-first Windows tool for indexing, searching, and loading large agent skill libraries without keeping full skill bodies in context. It supports SQLite FTS5 search, multiple ranking modes, CLI use, HTTP, and MCP stdio.

A CLI tool that keeps Claude Code and Codex configs in sync, with drift detection, backup-on-write, and a visual board for comparing host-side agents, skills, hooks, and MCP servers.

Open-source runtime action grounding framework for AI agents. It verifies proposed agent actions against live systems of record before execution and can return allow, hold-for-human, or block decisions.

A VS Code extension that organizes Claude Code and Codex sessions around Git worktrees, keeping sessions, terminals, changed files, and provider tabs in one cockpit.

A research project and interactive visualization on how agent-generated code behaves after merge in real-world open source repositories, with a paper, replication package, and data-driven findings.

A hosted MCP server for time and date utilities, including timezone lookup, calendar info, timestamp conversion, Unix time, and Alphadec conversion. The README says it works with Claude.ai, Claude iOS, Claude Code, OpenAI Codex, and any MCP-compatible client.

A command-line social media automation tool for developers and AI agents. It supports posting and scheduling across multiple networks, JSON output, schedule files in git, validation before publish, and integrations for CI and agent workflows.

Local-first macOS app for recording, live transcription, speaker labeling, and AI-assisted meeting notes. It connects to MCP clients so an AI can follow the conversation live and produce advice, action items, and recaps.

Self-hosted registry for AI agents and MCP servers that supports capability-based discovery, health checks, and simple JSON/HTTP registration.

A lightweight Flask-based LLM proxy that forwards Ollama, OpenAI, and llama.cpp-style requests to NVIDIA’s OpenAI-compatible API, with streaming support, retries, caching, auth, and usage stats.

A local Anthropic-compatible proxy that lets Claude Code work through ChatGPT, Kimi, Grok, or Cursor subscriptions, with provider routing, diagnostics, and model mapping.