open-source

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.

Open-source tool for visualizing and analyzing AI agent sessions, with personalization tips, dashboard analytics, and support for multiple coding agents.

Nimbalyst is a visual workspace for building with Codex, Claude Code, and other coding agents. It combines collaborative editors, session management, task tracking, git/worktree tools, and a mobile app for managing agent work on the go.

Stroq is a local action firewall for AI coding agents. It scans tool output, marks risky sessions, blocks dangerous follow-up actions, and keeps a hash-chained audit log, with support for Claude Code, Cursor, Codex, Copilot CLI, Windsurf, OpenClaw, and MCP clients.

Open-source agentic workspace for teams that combines apps, chat tools, integrations, models, and agents in one local-first environment with shared memory.

Bastiontrace is a Python library for analyzing AI agent tool-call traces to locate prompt injections, identify where they landed, and map the resulting blast radius.

Open-source pixel-art mission control for Claude Code agents. It turns projects into offices on a campus map, shows live agent status and spending, and lets you orchestrate tasks across workspaces from one desktop app.

An autonomous terminal coding agent built for Android Termux plus Windows, macOS, and Linux. The repo describes PLAN and AGENT modes, image input, a live web server, rollback, diagnostics, memory, and support for multiple AI providers.