open-source

JarvisCore is a Python framework for building distributed multi-agent systems with peer-to-peer discovery, crash recovery, zero-trust credential handling, shared memory, and built-in observability.

A small Python CLI that hooks into Claude Code to gradually increase target-language usage during chat sessions, with monitoring, ramp policies, help modes, and a pause/kill switch.

Local-first coding agent workbench that runs agents in secretless microVMs, with support for multiple providers, parallel sessions, and shared repository workflows.

Terminal-native attention router for parallel Claude Code sessions. It shows session status in the terminal, highlights the one that needs help, and provides quick jump shortcuts, tmux support, and optional desktop notifications.

BOUND is a deterministic control harness for AI agents. It sits between agent execution and the next decision, using observable evidence to choose ACCEPT, RETRY, REPLAN, or ROLLBACK.

A small open-source C# tool for local inter-agent collaboration in coding workflows, with shared chat state, role memory, Markdown messages, and goal tracking inside a Git repo.

Open-source CLI for spinning up disposable local or remote sandboxes for AI agents. It uses a manifest and Dockerfile to build fresh boxes, then exposes a single shell tool through MCP so an agent can work inside the sandbox without touching the host.

A source-available JavaScript browser agent for asserting end-to-end behavior in real user sessions. The repo explains the annotation-based approach, how it runs in staging and production, and how to install and initialize it via CDN or npm.

A sourced model and short report exploring whether Europe could train a sovereign frontier AI model using public compute it already owns, with reproducible code, datasets, and a PDF report.

OpenLoomi is an open-source desktop AI workspace that connects to apps like email, calendar, chat, docs, and project trackers to build a persistent context graph with proactive actions and local-first storage.

An Emacs package that acts like an AI pair programmer and teaching assistant while you code, with save-time reviews, follow-up questions, and architecture memory for local projects.

Cast is an open-source, self-hosted harness for multi-user Claude agents. It focuses on routing, identity, and access control outside the prompt, with support for agent building, review flows, and extensions like email, calendar, web fetch, and WhatsApp.

A technical guide that shows how to build a small CLI-based LLM agent for microservices using tool discovery, model calls, conversation history, and a REPL loop.

Smriti is an open-source system for shared reasoning state across coding agents like Claude Code and Codex. It treats project reasoning like version-controlled state, with local setup, a CLI, backend, and frontend for coordinating multiple agents on the same repo.

Open-source AI SEO optimizer CLI that audits pages, generates meta tags, analyzes keyword gaps, and drafts blog outlines. It can run free for audits and uses a KianBot API key for AI-assisted features.

An open-source research framework for structured LLM evaluation, claim verification, and source-grounded reflective reasoning. The repo describes modular components for retrieval, semantic scoring, skeptical claim checking, and benchmark-style epistemic assessment.

Open-source Claude Skill plus MCP integration for job search and interview prep, with live job data, role-specific interview intel, answer scoring, resume scoring, and voice mock interviews as an upgrade path.

A local coding-agent setup that turns Ollama models into a private, verified team of specialist agents for coding workflows. It includes hardware-aware model selection, role assignment, permission-restricted workflows, and validation probes.

Open-source fork of JetBrains ThinkRail that turns Claude Code into a first-class terminal agent inside an IDE-like workbench, with an IDE bridge, session revival, plugin API, and MCP-backed workspace tools.

A blog post documenting an open-source, under-$40 take on OpenAI’s Codex Micro, built as an AI-assisted PCB routing and keyboard/macropad project.

MindShield is a browser extension that adds a reflection pause before sending simple prompts to AI tools, using local on-device classification to reduce false positives and keep prompts private.

Local, private CLI that reads Claude Code session transcripts and estimates API-equivalent usage, token counts, and cost, with optional ledger export.

Canonical Agent Notation (CANON) is an open-source controlled English for model prompting and agent-to-agent communication. The repository describes a small closed vocabulary, mandatory obligation markers, bounded loops, and a clear ask-rather-than-guess rule for making requests and agent messages less ambiguous.

A browser extension for Chrome and Edge that connects a local folder to claude.ai so Claude can read, search, and edit files without a desktop app or API key.