open-source

Open-source MLOps/LLMOps platform for experiment tracking, model registry, and deployment with an emphasis on data and compute staying under user control.

A terminal multiplexer built for AI coding agents, with persistent sessions, agent-aware status, remote attach, and workspace/tab/pane management.

Steel’s Agent Traces turns recorded browser sessions into a readable, frame-synced timeline with inline details, markdown export, and API access for AI agent workflows.

Open-source estimation tool for AI coding-agent tasks. It gives PERT-based time forecasts, human-speed comparisons, model reliability checks, and wave planning for parallel work.

Open-source, local MCP-based context layer for AI coding assistants. It scans a codebase, builds a behavioral graph, and aims to improve architectural understanding while reducing input-token use on large repos.

Open-source local compute fabric for AI agents. It runs a single-node K3s stack through Docker Compose, provisions isolated Ubuntu sandboxes, and exposes native MCP support for local agent workflows.

Open-source local-first AI agent that routes between local and cloud LLMs, learns from escalations, and stores knowledge for future queries. The repo includes a quickstart, setup modes, and a concrete explanation of how it ingests docs and improves over time.

PileaX is a local-first AI knowledge base that combines AI chat, smart notes, and e-book reading/management in one product. The repo shows desktop and Docker-based deployment options, a Notion-style editor, and an AI-agent angle for managing knowledge and reading workflows.

Local push-to-talk dictation for macOS that uses Whisper, stays on-device, and pastes text at the cursor.

Open-sourced local multi-agent OS that runs three agents on consumer hardware, lets them form goals from environmental pressure, and supports self-modifying workflows through tool creation and change requests.

WUPHF is a local-first AI agent workspace that runs a team of role-based agents with a shared wiki and persistent project memory. It supports Claude Code, Codex, OpenClaw, and local models via OpenCode, with install and build options shown on the page.

Flue is an open-source Python tool that lets coding agents control desktop software from the command line without MCP servers. The README says it works with apps like Photoshop, Blender, Unity, Houdini, and Microsoft Office, and supports harnesses such as Claude Code, Codex, Gemini CLI, Cursor, and OpenCode.

Sandboxed bash for agents with structured command output and full filesystem state capture after each run.

A Claude Code plugin that learns from user corrections and successful runs, then turns them into reusable rules and playbooks stored locally.

A ~1000-line C workflow runtime where an LLM can modify a DAG during execution using a restricted four-verb grammar, with every change written to an append-only audit log for replay and inspection.

A local-first, file-based context and memory system for AI coding assistants. It’s designed to persist decisions, tasks, and learnings across sessions so tools can rehydrate project context instead of starting from scratch.

Open-source Rust coding agent with LLM-native code understanding, shell safety, and support for multiple LLM providers with automatic failover.

A tool that converts any URL into markdown optimized for coding agents, with browser, CLI, API, SDK, and agent integration support.

Harness is an open-source app for running a team of AI agents, with support for Claude, browser control, mobile access, and a headless server mode for remote use.

Local open-source coding agent for developers, with a macro-style command workflow and benchmark results showing fewer turns and better pass rates than Codex CLI in the published comparison.

A Python framework for local document search that replaces traditional embedding-based RAG with BM25 indexing, Meilisearch, and an agent loop for search, fetch, and citation-backed answers.

An AI-powered Obsidian plugin that turns notes into a self-organizing wiki with auto-generated entity pages, bidirectional links, traceable answers, and local-first support.

A harness that runs MCP servers in a disposable Linux sandbox and logs their real startup behavior, including file access and outbound network connections.

Open-source Kubernetes-native runtime for LLM agents. CLRK runs agents in gVisor sandboxes and intercepts outbound traffic for observability, policy enforcement, credential injection, and routing control.