Alternatives
Products that do what Cosmonapse does
An agent-to-agent protocol built for harness engineering
- 1
Open-source unified interface for agent harnesses
21d ago · harnessrouter.ai
- 2
- 3AH
May 2026 · ahk.cardor.dev
- 4GA
Hey HN! Wanted to show our open source agent harness called Gambit. If you’re not familiar, agent harnesses are sort of like an operating system for an agent... they handle tool calling, planning, context window management, and don’t require as much developer orchestration. Normally you might see an agent orchestration framework pipeline like: compute -> compute -> compute -> LLM -> compute -> compute -> LLM we invert this so with an agent harness, it’s more like: LLM -> LLM -> LLM -> compute -> LLM -> LLM -> compute -> LLM Essentially you describe each agent in either a self contained…
Jan 2026 · github.com
- 5
- 6
- 7
- 8
- 9MA
Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](https://github.com/lastmile-ai/mcp-agent) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions. For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and…
2025 · github.com
- 10BA
Sep 2025 · thealliance.ai
- 11
- 12
- 13
- 142C
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
Feb 2026 · github.com
- 15RT
This project (Agents Observe) started as an exploration into building automation harnesses around claude code. I needed a way to see exactly what teams of agents were doing in realtime and to filter and search their output. A few interesting learnings from building and using this: - Claude code hooks are blocking - performance degrades rapidly if you have a lot of plugins that use hooks - Hooks provide a lot more useful info than OTEL data - Claude's jsonl files provide the full picture - Lifecycle management of MCP processes started by plugins is a bit kludgy at best The biggest takeaway is…
Apr 2026 · github.com
- 16CO
We recently started to use agents to update some documentation across our codebase on a weekly basis, and everything quickly turned into cron jobs, logs, and terminal output. it worked, but was hard to tell what agents were doing, why something failed, or whether a workflow was actually progressing. We thought it would be more interesting to treat agents as long-lived workers with state and responsibilities and explicit handoffs. Something you can actually see and reason about, instead of just tailing logs. So we built Clawe, a small coordination layer on top of OpenClaw that lets agent…
Feb 2026 · github.com
- 17CC
Yesterday I built something that probably shouldn’t exist yet. In 9 hours, I created a cognitive architecture demonstrating emergent reasoning. It follows a 5-step loop: Plan → Reason → Act → Reflect → Respond. Adding a WebSearchTool to test extensibility, the agent initially failed its first search, reflected on poor results, adapted its query, and then succeeded. This behavior wasn’t programmed; it emerged naturally from the architecture. Five hours later, I integrated a FileManagerTool — it worked on the first try. Like code compiling first time, except this was intelligence composing…
2025 · github.com
- 18RA
Hey HN! A few months ago we shared mcp-agent (https://github.com/lastmile-ai/mcp-agent) [1][2], a lightweight framework that implements every agent pattern from Anthropic’s Building Effective Agents blog [3] and handles MCP server/client management seamlessly. Our core bet is that connecting LLMs to tools, resources, and external systems will soon be MCP-native by default. Today we're launching a significant update: Agents as MCP servers. Currently "agentic" behavior exists only on the MCP client side – clients like Claude or Cursor use MCP servers to solve tasks.…
2025 · github.com
- 19AP
Hey all! I recently gave a workshop talk at PyCon Greece 2025 about building production-ready agent systems. To check the workshop, I put together a demo repo: (I will add the slides too soon in my blog: https://www.petrostechchronicles.com/) https://github.com/Aherontas/Pycon_Greece_2025_Presentation_... The idea was to show how multiple AI agents can collaborate using FastAPI + Pydantic-AI, with protocols like MCP (Model Context Protocol) and A2A (Agent-to-Agent) for safe communication and orchestration. Features: - Multiple agents running in containers -…
Sep 2025 · github.com
- 20
Hey HN! We are building HarnessRouter, a canonical API for running Codex, Claude Code, Hermes, and other managed agent harnesses as your product backend. Before building HarnessRouter, I used to build our own agent harness for our products. I tried LangGraph, agent SDKs from different vendors, pydantic, LLM tool use / function call, and so on. It's a very heavy lifting engineering effort, and I am disappointed about the agent deliveries compared to what Codex, CC can deliver. That changed my mindset. The frontier labs and famous open source communities are already putting so much…
20d ago · github.com
- 21
- 22CM
I built an MCP server that connects coding agents (Claude Code, Cursor, OpenCode, Codex) to a collaborative workspace where your team and other AI models can review what the agent is planning. The problem: When Claude Code creates an implementation plan, it lives in your terminal session. Nobody else sees it until it becomes a PR. If you want GPT to check the architecture or a teammate to flag issues, you're copy-pasting between windows. This MCP server fixes that. When your agent creates a plan, it gets shared as a collaborative thread in CoChat. Engineers comment on it, other AI models…
Feb 2026 · github.com
- 23MR
The most common failures for production agents are behavioral: looping, reasoning leakage, user frustration, and more. Using a frontier model like GPT or Sonnet to judge every turn is too expensive and slow to run at scale. To solve this, we built Reflexes: semantic signals from agent traces, served fast and cheap over API. Built on custom kernels and a custom inference engine forked from vLLM. Under the hood, it is a small LLM architected around multi-head inference. Small models need to be trained for specific tasks, but running 50 separate small models on the same input for 50 tasks makes…
Jun 2026
- 24AO
Hello Folks! Agentic Orchestrator is a terminal tool that takes complex feature requests and builds them by orchestrating coding agents through a series of phases that emulate a full-fledged engineering flow: requirements clarification, research, design, multi-phase planning, implementation, and review. It is a single pane of glass for all your features and exposes post-publish utilities such as resolving merge conflicts and responding to review comments. The key design choice is that this is deterministic orchestration on top of undeterministic agents: things like "human review gates",…
Jun 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →