Top Picks

Open-source endpoint visibility and response for AI agents, with local detection, optional pre-action blocking, and forensic reconstruction.

Wrapper is a self-hosted CLI for hosting, managing, and observing multiple Slack-based AI agents, each isolated in its own hardened container with Langfuse tracing.

A terminal UI for managing multiple AI coding-agent sessions in tmux, with live status, grouped sessions, pane previews, quick prompts, and diff review.

Loopsfinity is an agentic software development platform that maps a codebase, turns PRDs into ticketed plans, writes tests first, and ships changes behind approval gates.

Local-first debugger for LLM agent context windows. It records each call’s context into a single-file trace so you can inspect, diff, and share what the model actually saw turn by turn.

Otlet is a Postgres extension for running local LLM inference next to database rows. The README shows SQL examples, model registration, task execution, and an entity-resolution workflow with typed outputs.

A hands-on kit for authorized red teaming of locally run LLMs, with jailbreak techniques, prompt-injection scenarios, streaming attack visualization, and support for OpenAI-compatible local model servers.

Open-source runtime guardrails for AI agents that scans for prompt-injection weaknesses and blocks unsafe tool calls at execution time with a decorator.

Gnoseed is a free spaced-repetition flashcard platform for developers, focused on Kubernetes, DevOps, AI, cloud, and certification prep. It includes 3,924+ practice questions, 47 topic decks, offline use, and learning paths for roles and exams.

A verification browser for AI coding agents built on WebKitGTK, aimed at fast visual checks, page assertions, and human handoff. The repository shows install steps, CLI usage, MCP support, and a concrete agent workflow.

An SSH client built for AI agents and humans. Corv focuses on named connections, warm authenticated sessions, structured JSON output, and safer command execution for agent-driven infrastructure.

Open-source desktop disk cleaner for developers and machine learning engineers on macOS and Windows. It detects and removes caches from tools like Hugging Face, Ollama, npm, pip, conda, Docker, and IDEs, with safety ratings and restore-friendly cleanup.

Stele is a hosted shared memory layer for AI coding agents. It keeps decisions, tasks, lessons, and risks in a project graph that Claude Code, Cursor, Codex, and other MCP-compatible tools can read and write.

Millwright is a self-hosted Rust LLM router that sits between apps and model providers to enforce policy-based routing, control spend, and preserve provider/model affinity for cache reuse.

Shared AI-context platform for teams that captures decisions, gotchas, and domain knowledge once and makes it available to agents through MCP and popular coding/chat tools.

A local proxy and CLI for switching and monitoring Codex and Claude Code accounts, with combined token-throughput analytics and rate-limit awareness.

Fractal is a developer tool for running hierarchical agent loops that break complex work into sub-tasks, spin up child nodes in git worktrees, and track state locally in SQLite with a terminal UI.

Self-hosted OpenAI-compatible AI gateway with a CLI, server mode, and web UI for text, image, and audio workflows across many models and providers.

An MCP server for GoCD that lets AI agents inspect and operate pipelines using per-user GoCD personal access tokens. It exposes read, action, and destructive toolsets, plus resource URIs for dashboard, agents, and pipeline data.

A local-first CLI that compresses application logs into a token-optimized Markdown/JSONL summary for LLMs.

Self-hosted Hacker News reader that summarizes top stories with AI, translates them into 20+ languages, personalizes the feed, and sends a daily briefing to Telegram.

Local-first MCP gateway that lets multiple AI clients share one server setup, with lazy tool discovery to reduce token usage and built-in tool integrity and quarantine controls.

Fuse is an open-source .NET MCP/CLI tool that helps coding agents work on C# codebases with Roslyn-backed indexing, dependency injection and route resolution, scoped context reduction, and compiler checks before edits are written.

Agentty is a terminal-based AI pair programming tool and a drop-in alternative to Claude Code, built as a single static C++26 binary with support for multiple model providers. The repository shows installation paths, provider examples, sandboxing, air-gapped mode, and integration with Zed via ACP.