* [Crush v0.75.0](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [RuFlo v3.10.19](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.18](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.17](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.15](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.14](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.13](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.12](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.10](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Crush v0.74.0](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [Kandev v0.55.0](https://github.com/kdlbs/kandev) – Kanban-based development environment that orchestrates multiple AI agents, reviews changes, and manages parallel tasks.

* [RuFlo v3.10.34](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.33](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Kandev v0.54.0](https://github.com/kdlbs/kandev) – Kanban-based development environment that orchestrates multiple AI agents, reviews changes, and manages parallel tasks.

* [RuFlo v3.10.31](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Kelos v0.37.0](https://github.com/kelos-dev/kelos) – Kubernetes-native framework for orchestrating autonomous AI coding agents.

* [RuFlo v3.10.30](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.29](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.28](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.27](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.26](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.25](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.24](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.23](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Nimbalyst v0.63.0](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [(S)AGE v8.5.0](https://github.com/l33tdawg/sage) – Persistent, consensus-validated institutional memory infrastructure for AI agents with confidence scoring and natural decay.

* [Crush v0.74.1](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [RuFlo v3.10.9](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.7](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.6](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Kandev v0.53.0](https://github.com/kdlbs/kandev) – Kanban-based development environment that orchestrates multiple AI agents, reviews changes, and manages parallel tasks.

* [RuFlo v3.10.5](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [RuFlo v3.10.4](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [Nimbalyst v0.63.9](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [metro-mcp v0.12.0](https://github.com/steve228uk/metro-mcp) – Plugin-based MCP server connecting Metro to the Chrome DevTools Protocol for React Native runtime debugging, inspection, and automation without app code changes.

* [K-Dense BYOK v0.4.6](https://github.com/K-Dense-AI/k-dense-byok) – Desktop AI research assistant running locally with your API keys to orchestrate expert agents, file workflows, and web search.

* [Nimbalyst v0.63.7](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [agent-device v0.16.9](https://github.com/callstackincubator/agent-device) – CLI for controlling iOS and Android devices and emulators to enable AI agents to interact with apps and UIs.

* [Nimbalyst v0.63.6](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [Nimbalyst v0.63.4](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [K-Dense BYOK v0.4.5](https://github.com/K-Dense-AI/k-dense-byok) – Desktop AI research assistant running locally with your API keys to orchestrate expert agents, file workflows, and web search.

* [Shep v1.208.0](https://github.com/shep-ai/shep) – Run multiple AI coding agents in parallel, each in its own isolated git worktree with automated commits, pushes, and PRs.

* [Nimbalyst v0.63.1](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [Nocturne: The Soul Anchor Protocol 2.5.4](https://github.com/Dataojitori/nocturne_memory) – URI-based, rollback-capable, visual MCP memory store providing persistent, structured memories across models, sessions, and tools.

* [agent-device v0.16.3](https://github.com/callstackincubator/agent-device) – CLI for controlling iOS and Android devices and emulators to enable AI agents to interact with apps and UIs.

* [K-Dense BYOK v0.4.4](https://github.com/K-Dense-AI/k-dense-byok) – Desktop AI research assistant running locally with your API keys to orchestrate expert agents, file workflows, and web search.

* [AgentOS v0.9.34](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [AgentField v0.1.88](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AgentOS v0.9.33](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [AgentOS v0.9.32](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [AgentField v0.1.87](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AgentOS v0.9.31](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [AgentOS v0.9.30](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AgentOS v0.9.30](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [AgentOS v0.9.29](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AgentOS v0.9.28](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AgentOS v0.9.27](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AgentOS v0.9.26](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [Autopus-ADK v0.50.19](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [agentsh v0.20.3](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [CAIPE 0.5.4](https://github.com/cnoe-io/ai-platform-engineering) – Community-driven multi-agent platform engineering system providing persona-driven agents, knowledge retrieval, and integrations for platform operations.

* [AgentOS v0.9.25](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AgentField v0.1.85](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AgentOS v0.9.24](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [Autopus-ADK v0.50.18](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.17](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [AgentOS v0.9.23](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [AI Maestro v0.35.31](https://github.com/23blocks-OS/ai-maestro) – Agent orchestrator providing persistent memory, agent-to-agent messaging, and a dashboard to manage agents across multiple machines.

* [Autopus-ADK v0.50.36](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.35](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.34](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.33](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [AgentField v0.1.87-rc.2](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Autopus-ADK v0.50.32](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.31](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.30](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.28](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.27](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.26](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.25](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.24](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.23](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.22](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.21](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Autopus-ADK v0.50.20](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [atomic-agent v0.1.32](https://github.com/AtomicBot-ai/atomic-agent) – Local operator agent for llama.cpp that controls browser, files, shell, tasks, and approvals while keeping data and models local.

* [atomic-agent v0.1.31](https://github.com/AtomicBot-ai/atomic-agent) – Local operator agent for llama.cpp that controls browser, files, shell, tasks, and approvals while keeping data and models local.

* [AgentField v0.1.85-rc.11](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [atomic-agent v0.1.30](https://github.com/AtomicBot-ai/atomic-agent) – Local operator agent for llama.cpp that controls browser, files, shell, tasks, and approvals while keeping data and models local.

* [agentsh v0.20.3-rc16](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc15](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc14](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc13](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc9](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc8](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.

* [agentsh v0.20.3-rc7](https://github.com/canyonroad/agentsh) – Secure policy-enforced execution gateway that intercepts file, network, process, and signal activity and emits structured audit events.