open-source

A native macOS menu-bar app that lets you mark exact pixels in a screenshot and copy an AI-ready prompt with annotated image context and marker notes.

Sipp is a zero-dependency AI inference runtime for running models in the browser and across Node, Rust, Python, and self-hosted gateways. The page shows install commands, a symmetric client API, benchmark claims, and live demos for chat, agents, vision, and game use cases.

HALO is an open-source local debugger and optimizer for AI agent traces. It collects execution traces, analyzes recurring failure modes with an RLM-based engine, and feeds findings into a coding agent to improve the harness.

Open-source AI agent monitoring platform with tracing, issue grouping, evals, semantic search, alerts, and MCP access for coding agents.

An Android accessibility service that lets agents and scripts inspect the UI tree and control a phone from the CLI, REST, or MCP with token-gated permissions.

Velane is an agent-first code runtime for building workflows with AI agents. It connects to Cursor or Claude via MCP, offers 800+ integrations, and lets agents create, test, and promote Bun or Python workflows with sandboxed execution and environment controls.

A self-hostable SMS relay for AI agents that uses an old Android phone and a prepaid SIM, exposed over MCP so clients like Claude, ChatGPT, and Cursor can send and receive real texts.

Ironsmith is an open-source macOS menu bar app that generates small native SwiftUI apps from prompts, using local or hosted LLMs.

SpadeBox is an open-source sandboxed tools and JavaScript runtime for AI agents, with Rust core plus JavaScript and Python bindings. It provides file, network, and code-execution tools, supports MCP, and includes examples for JavaScript, Rust, and Python.

A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers.

RiskKernel is an open-source, self-hosted reliability runtime for AI agents. It adds hard budgets, kill switches, crash-resumable runs, human approval gates, and OpenTelemetry export, with support for OpenAI, Anthropic, and existing agent stacks.

Linux-only kernel-level audit feed for Claude Code or other matched agent sessions, streaming exec, file, and network activity in real time.

A TypeScript stealth browser runtime for AI agents that drives real Chrome over raw CDP, with MCP support and accessibility-tree based interaction.

Lowfat is a lightweight CLI tool that filters noisy command output before it reaches an AI agent, with plugins, shell integration, and usage stats for token savings.

JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.

Open-source C++ and CUDA LLM inference engine inspired by vLLM, with a teaching-focused course that walks through model serving, batching, KV cache, and attention kernels.

Open-source SDK for governing AI agent tool calls before side effects happen, with policy enforcement, approval flows, audit logs, and local execution.

TokenBBQ is an open-source dashboard and CLI that tracks token usage and estimated costs across Claude Code, Codex, Gemini, OpenCode, Amp, and Pi-Agent from local files on your machine.

An open-source 26M parameter function-calling model designed to run on very small devices, with a local quickstart, Python usage, and a playground for testing and finetuning.

Open-source email gateway for AI agents with SPF/DKIM verification, HMAC-signed delivery, webhook and WebSocket fan-out, plus CLI and SDK support.

A local coordinator for parallel AI coding agents. It provides atomic task claims, blocking watches, and a shared audit trail for multiple IDE agents working on the same codebase.

A local MCP server for AI coding agents that records why code changes were made and stores that history in SQLite next to the project.

Open-source platform for governing AI agents across clouds and stacks, with a control plane, sidecar-based data plane, policy enforcement, observability, and audit trails.

An open-source memory governance layer for AI agents. It adds deduplication, conflict detection, decay, archival, and explainable retrieval so agent memory can be managed with more control than passive storage.