Your team’s AI agent shouldn’t be trapped in one chat app. Lemma Platform is an open-source multiplayer harness for teams building shared AI teammates, apps, and workflows. It helps you keep AI work in one permissioned system by giving the same teammate shared records and a way to work across the tools your team already uses. Key features: • Multi-channel access – use the same teammate from Slack, Teams, WhatsApp, Telegram, or email • Shared + personal memory – keep team notes shared while personal notes stay visible only to you • Chat-built apps – ask in chat for a screen, then open it like an internal tool on the same records • Workflow triggers – start work on schedules, row changes, or incoming Slack and GitHub events • Permission controls – apply roles, row-level access, and approvals before consequential actions It’s open-source (GNU AGPL v3.0 license). Link in the reply 👇

Building an AI workplace means stitching together APIs, agents, and real-time messaging. This repo gives you the server core. OCTO Server is the Go backend for OCTO, an open workplace for humans and AI agents. It helps you build the backend layer for an agent-enabled collaboration product by centralizing REST and WebSocket APIs, Lobster agent scheduling, and the WuKongIM messaging control plane. Key features: • REST + WebSocket APIs – handles conversations, users, groups, files, organizations, and webhooks • Agent orchestration – routes Lobster sessions and tool-call execution inside the server • Real-time messaging control – drives WuKongIM for channels, messages, and presence • Pluggable data services – includes MySQL-compatible migrations, cache repositories, and object-storage adapters • Deployable Go service – build the binary with Go and start it from the included YAML configuration template It’s open-source (Apache License 2.0). Link in the reply 👇

Running coding agents from different vendors shouldn’t mean juggling separate terminals. Coral is an agentic IDE for developers who want to run Claude Code, Codex, Gemini CLI, and Pi.dev as one coordinated team. It helps you coordinate existing coding-agent CLIs by putting their sessions, tasks, messages, and controls behind a shared board and browser dashboard. Key features: • Mixed-vendor teams – run supported coding-agent CLIs together on the same codebase • Shared task queue – define task dependencies, required artifacts, and review holds • Agent message board – give agents a place to post updates, ask questions, and coordinate handoffs • Worktree-backed sessions – launch teams in dedicated git worktrees while tracking changes against main • Browser and phone access – view live terminals, agent status, and permission prompts from the dashboard It’s open-source (Apache License 2.0). Link in the reply 👇

Personal agents get harder when they need to use real apps and respect real boundaries. Open Instinct is an open-source personal-agent repository for builders who want to run an agent they can text. It helps you move from a message to an agent-run task by combining a text-facing identity, an agent loop in a Linux desktop microVM, connected apps, and policy checks before tools run. Key features: • Text-based identity – Inkbox supplies a phone number, email address, and agent-to-agent endpoint • Isolated computer – the agent runs in its own microVM with a Linux desktop for real task execution • Trust tiers and grants – seven code-enforced access levels and plain-English exceptions govern tool use • Connected apps and editable behavior – Composio integrations and file-based prompts let you connect apps and adjust the agent • Payment approval flow – Stripe Link creates a one-time card for an exact total, with owner approval on the phone It’s open-source (MIT license). Link in the reply 👇

Agent context gets lost between sessions. This repo gives it a shared home. Forgetful is a storage and retrieval MCP server for AI agents that need a shared knowledge base. It helps you carry useful context across coding agents, chatbots, and custom agents by storing atomic memories, embedding them for natural-language retrieval, and linking related notes automatically. Key features: • MCP server transports – connect over stdio or HTTP for local or remote setups • Atomic memory model – store one concept per note to keep knowledge clear and linkable • Semantic retrieval – query stored memories in natural language with vector search and optional reranking • Automatic knowledge graph – links semantically similar memories to surface related context • Flexible storage – start with zero-config SQLite or use PostgreSQL for larger deployments It’s open-source (MIT license). Link in the reply 👇

AI coding agents need more than prompts. This CLI shows what your repo is missing. Harness Score is a command-line scanner for measuring the setup around AI coding agents: context files, rules, skills, hooks, tests, CI, and safety checks. It helps you find the next practical improvement by scanning a repository and returning a maturity level, a scored breakdown, and the checks that block the next level. Key features: • Six-dimension audit – evaluates 36 checks across guides, skills, guardrails, feedback, CI, and hygiene • Maturity ladder – maps a repo from L0 to L4 and identifies requirements for the next level • Deterministic results – uses filesystem facts, with no LLM calls or network access during a scan • CI gate – supports a minimum maturity level so pipelines can fail when a harness regresses • Multiple outputs – can emit terminal, JSON, Markdown, and badge output; it also ships a GitHub Action It’s open-source (MIT license). Link in the reply 👇