* [Reasonix v1.29.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [Open Multi-Agent v1.16.0](https://github.com/open-multi-agent/open-multi-agent) – TypeScript-native multi-agent orchestration that decomposes goals into parallel task DAGs and synthesizes results.

* [ContextLattice v5.0.0](https://github.com/sheawinkler/ContextLattice) – Local-first memory orchestration for AI systems with durable writes, multi-sink fanout, retrieval learning loops, and operator-grade controls.

* [Capability Evolver v1.94.0](https://github.com/EvoMap/evolver) – Protocol-constrained engine generating GEP prompts to guide auditable evolution of AI agents using reusable Genes and Capsules.

* [Chidori v3.7.0](https://github.com/ThousandBirdsInc/chidori) – Agent framework for durable, replayable, and resumable TypeScript runs via recorded host calls over a Rust core.

* [DSPy-Go v0.88.0](https://github.com/XiaoConstantine/dspy-go) – Native Go framework providing systematic prompt engineering, composable modules, and automated reasoning for building LLM applications.

* [StreamCore v0.1.0](https://github.com/streamcoreai/streamcore-server) – Go-based realtime media runtime providing WebRTC audio transport, session management, streaming speech/STT/LLM/TTS, interruption handling, and client SDK integration.

* [AgenticX v0.5.0](https://github.com/DemonDamon/AgenticX) – Unified, production-ready multi-agent framework with SDK, CLI, Studio server, desktop app, Meta-Agent orchestration, hierarchical memory, and multi-LLM provider support.

* [OpenClacky v1.5.11](https://github.com/clacky-ai/openclacky) – Creator-focused platform for packaging encrypted, white-labeled AI workflows into sellable Skills with built-in storefront and cross-platform distribution.

* [hypha v1.0.1](https://github.com/CodeSoul-co/Hypha) – TypeScript framework combining an agent core with a production harness to run governed, durable domain agents with checkpoints, recovery, and cache reuse.

* [AI Team OS v1.11.2](https://github.com/CronusL-1141/AI-company) – Multi-agent operating system that runs autonomous AI teams to execute, coordinate, and self-improve software projects.

* [Network-AI v5.15.1](https://github.com/Jovancoding/Network-AI) – TypeScript/Node.js multi-agent orchestrator providing shared blackboard state, guardrails, budgets, and cross-framework adapters.

* [Autopus-ADK v0.50.108](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.