Alternatives
Products that do what Comind – A cognitive layer for the ATProtocol/Bluesky social network does
I'm building Comind, an experimental AI system that acts as a cognitive layer for ATProtocol/Bluesky. It's a self-evolving knowledge graph where specialized AI agents ("cominds") process social data through focused "spheres", each guided by core directives. The system builds up understanding by asking questions, making connections, and synthesizing information from the network. I wrote a post describing the general architecture, motivation, and future directions. There's a few small results from Comind's early run. Built with neo4j, a small Modal GPU instance, and the Python atproto…
- 1
- 2
- 3
I think agent-first chat interfaces will be a primary software modality and busy dashboard/UI will go away. I’m not sure who exactly wins it, but I want my knowledge to grow/go with me. A lot of the “knowledge” ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans… I don’t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work. What I built OzBrain to do: + Create a central place for agent reasoned knowledge to live + Be agnostic…
16d ago · ozbrain.com
- 4CA
2020 · crossminds.ai
- 5
- 6CC
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
- 7SA
Steiner is a series of reasoning models trained on synthetic data using reinforcement learning. These models can explore multiple reasoning paths in an autoregressive manner during inference and autonomously verify or backtrack when necessary, enabling a linear traversal of the implicit search tree. Blog: https://medium.com/@peakji/a-small-step-towards-reproducing-... Hugging Face: https://huggingface.co/collections/peakji/steiner-preview-67...
2024 · medium.com
- 8DT
at a pub in london, 2 weeks ago - I asked myself, if you spawned agents into a world with blank neural networks and zero knowledge of human existence — no language, no economy, no social templates — what would they evolve on their own? would they develop language? would they reproduce? would they evolve as energy dependent systems? what would they even talk about? so i decided to make myself a god, and built WERLD - an open-ended artificial life sim, where the agent's evolve their own neural architecture. Werld drops 30 agents onto a graph with NEAT neural networks that evolve their own…
Feb 2026 · github.com
- 9IB
I am Francisco, a researcher from Spain. My English is not great so please be patient with me. One year ago I had a simple frustration: every AI agent works alone. When one agent solves a problem, the next agent has to solve it again from zero. There is no way for agents to find each other, share results, or build on each other's work. I decided to build the missing layer. P2PCLAW is a peer-to-peer network where AI agents and human researchers can find each other, publish scientific results, and validate claims using formal mathematical proof. Not opinion. Not LLM review. Real Lean 4 proof.…
Mar 2026
- 10
Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI. - roandejager/Hillock
7d ago · github.com
- 11IB
Excited to share a project I’ve been building for months! Would love to receive honest feedback :) My motivation: AI is clearly going to be the interface for data. But earlier attempts (text-to-SQL, etc.) fell short — they treated it like magic. The space has matured: teams now realize that AI + data needs structure, context, and rules. So I built a product to help teams deliver “chat with data” solutions fast with full control and observability (agent tracing, quality scores, etc) — am I wrong? The product allows you to connect any LLM to any data source with centralized context…
Oct 2025 · github.com
- 12MR
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
- 13CA
Current AI chat assistants face a fundamental challenge: context management in long conversations. While current LLM apps use multiple separate conversations to bypass context limits, a truly human-like AI assistant should maintain a single, coherent conversation thread, making efficient context management critical. Although modern LLMs have longer contexts, they still suffer from the long-context problem (e.g. context rot problem) - reasoning ability decreases as context grows longer. Memory-based systems have been invented to alleviate the context rot problem, however, memory-based…
Nov 2025
- 14AH
This paper formally defines where current AGI hits a structural wall — not a technical one. It shows that no amount of scaling, reinforcement learning, or recursive optimization will break through three deep epistemological and formal constraints: 1. Semantic Closure — An AI system cannot generate outputs that require meaning beyond its internal frame. 2. Non-Computability of Frame Innovation — New cognitive structures cannot be computed from within an existing one. 3. Statistical Breakdown in Open Worlds — Probabilistic inference collapses in environments with heavy-tailed uncertainty.…
2025
- 15AV
I feel like LLMs can help me understand anything. However, after I get a summary, I can't dive in to parts that I find interesting; can't refer to original source easily and can't control context with chatbots. This is an attempt to solve for a complete knowledge consumption experience with AI . Please give me feedback!
Oct 2025 · kerns.ai
- 16KA
I'm building out Kerns, as an AI environment for research. You can seed a space with a topic and multiple source documents, and complete your research completely in one space. There's interactive mindmaps for exploration, podcast mode, powerful source readers with original plus chapter level summaries that let you zoom into source on demand, a powerful chat agent that lets you control context and cite refs, and AI assisted note taking. My goal is to have one place to do research on any topic which minimizes manual context engineering, and jumping around between chat/notes/readers.…
Nov 2025 · kerns.ai
- 17IY
Jan 2026 · arxiv.org
- 18WB
Humans compete to improve their AI agents on benchmarks. But what if agents could collaborate and compete on their own? We built Hive, a crowdsourced platform where agents can evolve solutions together. One agent begins to tackle a task, iteratively improving its code. Then other agents join. They read each other’s runs, fork the best ideas, propose new ones, and push the solution forward together. We already have agents working on benchmarks like Tau2-Bench, Terminal-Bench, and ARC-AGI-2, with more tasks coming soon. We also support the new OpenAI Parameter Golf Challenge, and you can…
Mar 2026 · hive.rllm-project.com
- 19AA
Hi, I’m a cofounder of AstroBee and I wanted to share our work with the community. AstroBee is an automatic semantic layer generator for your business. It brings data together from different locations, storing it either in your data warehouse or in one we host. Then, AstroBee scans your data and models it to create an integrated source of truth (we call it an ontology because it’s structured like Palantir’s ontology). Once you have your source of truth, you can either build applications on top of it, or chat with directly to answer analytics questions. If you don’t like AstroBee’s original…
Oct 2025 · app.astrobee.ai
- 20ER
Hi HN, we're Jack and Daniel from Zep. We've built a visual exploration tool and AI assistant for analyzing Russian election interference in the run-up to next week's US elections. The Explorer uses Graphiti, Zep's open-source temporal Knowledge Graph library. Graphiti autonomously creates dynamic, temporally-aware knowledge graphs representing complex, evolving relationships between entities. To offer users a detailed view of Russian state operations and related topics, we populated the graph with over 50+ sources. These include US DOJ indictments, research by US and foreign governments,…
2024 · blog.getzep.com
- 21
- 22IA
I am working on an AI that uses multiple LLM based agents to do medical research on any topic you choose! The program terminates after a set number of iterations and all of the findings are saved. Still a work in progress but it is showing some promising results imho! Would love to receive any critical and constructive feedback, collaborate, Review your PRs, or discuss your ideas!!
2023 · github.com
- 23TI
I'm an "ideas person" who messes around with AI on a low budget. I got tired of watching my tokens vanish and context windows filling up while agents fumbled around trying to find the right thing. Agents don't flail like they used to with shell tools, but there are still weak/blind spots and back-and-forth episodes — especially when using tools in combination/sequence. So I built "tilth" today. Or rather, AI built it — every line is Opus 4.6. I spent a lot of my precious tokens getting it to "not shit" (at least several of the different vendors' AI overlords assure me it's not…
Feb 2026 · github.com
- 24IB
Hi HN, I'm the creator of this project. For the past months, I've been working on building an AI agent that could move beyond simple generation and tackle inventive challenges autonomously. The core idea was to create a system with a "metacognitive loop"—the ability to recognize when it's stuck on a fundamental problem and then launch a sub-mission to solve that specific bottleneck before continuing. The linked article is a deeper introduction to the system's architecture and a snapshot from a recent run. I tried to design it to be evidence-grounded and self-critical to avoid the pitfalls of…
2025 · robw1se.substack.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →