AI Agents

Category: AI Agents under Artificial Intelligence

MIT-core autonomous AI software engineer that resolves whole coding tasks in a sandboxed runtime you host yourself, though SSO, RBAC, and audit logs sit behind a commercial enterprise tier.

AGPL-licensed platform for self-hosted cloud development environments: provision Terraform-defined workspaces and govern AI coding agents on infrastructure you control, with no per-seat SaaS fees.

AGPL terminal multiplexer for running AI coding agents in parallel, tracking which is working or waiting. A local Rust binary, no cloud; a one-maintainer project with a commercial-license waiver.

A memory layer for AI agents: extracts and recalls facts across sessions so the LLM stops re-sending history. Apache-2.0, self-hostable on Postgres and Qdrant; SSO and audit logs are Enterprise-gated.

Foundation-governed AI agent for coding and workflow automation. Runs locally via desktop, CLI, or API, is model-agnostic through MCP, and carries no per-seat lock-in.

AGPL-3.0 self-hosted AI workspace: local-model chat, agents, research, and email in one stack with zero telemetry. Trade-offs are single-maintainer governance and AGPL network-copyleft embedding risk.

Local-first AI desktop assistant that keeps your "second brain" in an Obsidian-style Markdown vault and on-device SQLite. Optional local Ollama models, no cloud account. GPL-3.0, single-founder beta.

MIT-core terminal coding harness that wraps any LLM provider into an extensible agent, no IDE required. Future Fair Source and proprietary enterprise tiers announced but not yet released.

Self-improving AI agent with persistent memory and autonomous skills. Now adds a native desktop app (macOS, Windows, Linux) on top of 23+ messaging channels. Self-hosted, MIT-licensed, BYOK.

An open-source, local-first AI orchestration desktop that allows you to run LLMs entirely on your own hardware. A private alternative to ChatGPT.

A self-hosted, model-agnostic gateway wiring chat apps to AI agents, now run by a US foundation funded by major AI labs. Its multiplayer sessions are, by its own docs, not a security boundary.

A local-first AI desktop agent for executing browser workflows and file management. A private, MIT-licensed alternative to cloud-bound AI agents.

Self-hostable AI agent control framework with no enterprise tax. VC-backed by a single corporate contributor; monitor for open-core pivot.

An autonomous coding agent that integrates into your IDE to edit files, run terminal commands, and debug code with human-in-the-loop control.

An open-source LLM app development platform for orchestrating RAG pipelines, agents, and complex workflows with a visual interface.

BSD-3-Clause self-hosted LLM interface. Unlimited users, full offline capability, no seat pricing, without ChatGPT's model training exposure.

The open-source low-code tool for developers to build customized LLM orchestration flows and AI Agents using JavaScript/Node.js.