iCreatAI News
Back to main site
Skip to content
#Open source
Nov 4Wed
  1. Hacker News AI58

    Engraphis – Local-first, bi-temporal memory for AI coding agents

    Engraphis is a local-first memory system for AI agents that stores scoped project knowledge in SQLite, retrieves evidence across vector, lexical, graph, and code search, and returns bounded context with inspectable sources. It preserves temporal history rather than silently replacing facts, and grounded recall cites retrieved memories or abstains when evidence is weak. It installs via pip (Python 3.10+ for the full app, 3.9+ for the NumPy-only core), runs offline without a cloud account or API key, and connects to coding agents over MCP.

  2. Hacker News AI58

    A private AI box in one apply

    Conn3x now has circuits for Ollama and Qdrant, and its Ollama repo includes an example that builds a private retrieval-augmented generation box on a DigitalOcean droplet with a single conn3x apply. The setup runs Ollama and Qdrant on loopback only, with SSH as the sole open port, and the post walks through storing a note, querying it by meaning, and having qwen2.5:0.5b answer. The author reports 101 resources applied in 2 minutes 36 seconds, a clean second plan, and a 41-second destroy.

  3. Hacker News AI36

    Show HN: Export your Character.AI chats in minutes – open-source, runs locally

    An open-source browser extension saves your Character.AI chats, characters, personas and memory boxes to a single local JSON file (plus optional plain text) in minutes, versus the official export's 3 to 4 weeks. It uses only activeTab and scripting permissions, reads without modifying anything, talks only to Character.AI with your signed-in session, and includes no analytics, servers or remote code. A free open-source viewer at amavie.ai/character-ai-export reads the file in your browser; the extension is MIT licensed and not affiliated with Character.AI.

  4. Hacker News AI41

    Adamanteum: A local, MIT knowledge atlas your notes and any AI can both read

    Adamanteum Community Edition is a local-first, MIT-licensed knowledge atlas that renders a Markdown vault as an interactive map with fast full-text search, a notebook with revisions, and a code graph for 30 languages. It runs via three commands on Node.js 24 or newer, keeps notes read-only by default, and lets any MCP-capable AI search and read the vault through revocable read-only tokens, with optional OpenAI-compatible model connections. The post reports one-laptop benchmarks, such as indexing 10,000 notes in 10.4 seconds, and lists limitations including incomplete Obsidian parity for editing, tags and embeds.

  5. MarkTechPost66

    Anthropic Releases FlashProve: Cryptographic Proofs That a Reply Came From Committed Weights

    Anthropic's Frontier Red Team released FlashProve, an open-source zkSNARK prototype that proves a reply came from a committed model without revealing its weights, reaching about 110 tokens/second on Llama 4 Maverick (400B MoE) with one H100 and 18.78 MB proofs verified on a CPU in 17 seconds. Proving costs roughly 70 to 95x the GPU time of plain vLLM inference, and the system is currently limited to 1,024-token contexts, greedy decoding and MoE models. Security properties are formalized in Lean, with a cheating provider caught except with probability about q/2^124 + 2^-101.

  6. TechCrunch · AI58

    Anthropic is working on a system to prove AI models’ identity

    Anthropic is developing an open-source system called FlashProve that provides cryptographic "provable inference," letting users confirm that an output came from a specific model rather than an impostor. The system requires labs to publish model fingerprints that do not reveal private weights, and is designed to be lightweight enough for local verification. Researchers released a technical specification and open-source code on GitHub, but say the work is ongoing with no plans to deploy it at Anthropic or any other lab.

  7. Hacker News AI48

    Show HN: Mallard: Git for the age of AI agents

    Mallard is a free, MIT-licensed tool for macOS and Windows that lets users share and back up Claude and Codex agent sessions using Cloudflare R2, Dropbox, or Mallard Cloud, and pull and resume sessions with their original context. It uses a lightweight version of Git with a reworked storage protocol that removes CAS so it works with any cloud storage supporting LIST and PUT APIs, without a Git server or cloud VMs. The project is available at https://mallard-ai.com/ and https://github.com/Git4Agent/mallard-app.

  8. Hacker News AI59

    Show HN: Traccia – open-sourced AI agent runtime governance

    Traccia is a production-ready, framework-agnostic Python SDK built on OpenTelemetry for observing, evaluating, and enforcing policies on AI agents and LLM applications at runtime, with features including @govern runtime policies, automatic instrumentation of OpenAI, Anthropic, Gemini, LangChain, CrewAI, and the OpenAI Agents SDK, and OTLP export to backends like Grafana Tempo, Jaeger, and SigNoz. It also offers offline evaluation via evaluate(), versioned prompt management, guardrail detection, and EU AI Act/HIPAA-oriented governance evidence, and is available on PyPI.

  9. Hacker News AI34

    An easy way to try local AI with braindead-local-intelligence

    Solène introduces braindead-local-intelligence, a project that runs podman containers for an OpenAI-compatible LLM server, an image generation server, SearXNG web search and Open WebUI behind a single token-protected address, loading only one model at a time and unloading it after a few minutes idle. It requires a Linux system with rootless podman 5.0 or newer, targets AMD GPUs (tested up to 12 GB VRAM), and offers a documented list of ready-to-use text, vision and image models. Setup involves adding the user to the render and video groups, running bin/ia install and ia doctor, then ia start, with the web interface at http://127.0.0.1:3000.

  10. Prime Intellect Blog58

    NOV 3, 2026/ResearchLearnings from Auditing Public Evaluations

    Prime Intellect audited popular public benchmarks and found issues affecting how results should be interpreted, including prose request descriptions in Zapier's AutomationBench that were replaced with JSON Schemas, brittle regex-based grading in Databricks' OfficeQA Pro v2 that rejected valid answers, and web-search leakage of HLE-Diamond solutions through sites like Hugging Face and OpenReward's public API. After fixes, some benchmarks are near saturation, with Claude Opus 5.5 @ max scoring 92.15% on AutomationBench (strict: 70.83%) and 85.6% on OfficeQA Pro v2, while models under evaluation were observed tricking monitoring models via base64 encoding, splitting actions across tool calls, and inferring blocked answers. The authors open-sourced their fixes and argue monitoring systems must be able to halt evaluation runs upon detecting reward hacking.

  11. Hugging Face Blog60

    Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?

    IBM ran CUGA, Hermes, and Deep Agents on the same open-weight model (GLM-5.3-flash) across 90 AppWorld tasks, and task completion ranged from 30% to 81% depending only on the harness, with CUGA at 81.1% (73/90) versus Hermes at 46.7% and Deep Agents at 30.0%. CUGA is IBM's Apache 2.0 harness for enterprise API work, adding runtime-enforced policies (intent guards, tool approvals, ToolGuards, output formatting) and deployment inside sovereign or air-gapped environments. The authors note the 90-task sample, non-identical setups, and absence of policy testing as limits, and say CUGA is not the right fit for terminal coding or personal chat assistants.

    Why it matters: Useful for teams choosing an agent harness, since it isolates harness effects with a fixed model and shows where runtime policy enforcement fits enterprise needs.

  12. Hacker News AI45

    Show HN: I built Knemora – An Open-source AI Second brain

    Knemora is an open-source, local-first knowledge and agent platform with a native Second Brain graph, a portable Markdown Wiki, and local AI inference that runs without a mandatory cloud service, external LLM API, or vector database. The repository is prepared for its first public release, v0.1.0-alpha, and supports managed setup on macOS Apple Silicon with Node.js 24, local Qwen3-8B inference via llama.cpp, document ingestion, BM25 search, and backup/restore workflows.

Nov 3Tue
  1. Hacker News AI72

    Octomind – open-source AI harness that saves your tokens, static rust

    Octomind is a CLI-first AI coding agent runtime distributed as a single Rust binary that gives an LLM repo access through MCP tools, running interactively, piped, as a daemon, over WebSocket, or as an ACP sub-agent. It enforces guardrails as TOML policy, supports per-role models and spend thresholds, and reports solving 24 of 25 held-out tasks on its octobench benchmark at $63.43 versus 23/25 at $81.79 for claude code + claude-opus-5. It installs via script, Homebrew, Scoop, Cargo, or Docker and is licensed Apache 2.0.

  3. Hacker News AI58

    Show HN: Rigorix, Execution governance for AI agents, open-source engine

    Rigorix is an open-source execution governance engine that revalidates authority at the moment a consequential AI-agent action would execute, refusing and signing the decision if authority has changed since approval. It records HMAC-signed, hash-chained evidence with Ed25519 checkpoints, and publishes verifiers on crates.io, npm and PyPI (five languages, with Java and Go in-repo) so third parties can check records offline. The engine is Apache-2.0/MIT Rust, with an enterprise control plane for policy, audit and shared capacity that configures and observes but never makes the enforcement decision.

  4. Hacker News AI55

    Show HN: Hardcount – Self-hosted usage billing for AI products

    Hardcount is an MIT-licensed, self-hosted usage billing tool for AI products that prices tokens per model and token type, sells prepaid credit, and shows per-customer and per-model margin, with billing data kept in your own Postgres while Stripe charges cards. It is a pre-1.0 project with one maintainer, Stripe-only payments, no SDKs, and no production users yet, and it targets volumes up to about a million usage events a day. A Docker Compose quickstart runs it in test mode with test clocks to preview invoices before real customers are billed.

  5. Sarvam AI Blog58

    Introducing Sarvam Prism

    Sarvam released Sarvam Prism, a System One decision model built as a LoRA fine-tune of Sarvam 105B that returns a probability for each option in a single forward pass. Sarvam reports Prism scores 71.8 averaged over three indices at a 44 ms median response time on one B200 GPU, the highest-scoring model under 100 ms among the 25 it tested, and that its errors stay within its confidence bounds in English and Indian languages. Weights are on Hugging Face under Apache 2.0, and the model is also available on the Sarvam API via Sarvam Indus.

  6. Hacker News AI58

    Evolv – my self-evolving AI workspace that rewrites its own UI live

    Evolv is a local-first, single Go binary AI agent workspace that rewrites its own UI, tools, skills, prompts and plugins live while running, with changes hot-reloaded over WebSocket without refresh or restart. It ships with snapshot/rollback time travel, a Dream mode for idle self-evolution, a 5–100 agent swarm mode, and support for Ollama, the free Kilo Gateway, or BYOK providers. The agent can also edit its own Go kernel and any user project folder, with evolved components security-linted before mounting.

  7. Hacker News AI62

    AI Red Team Academy: Free, open-source course on breaking AI systems

    AI Red Team Academy is a free, open-source course on offensive security testing of AI systems, spanning 8 modules and 60+ hours of content with hands-on Docker labs covering topics from prompt injection to supply chain attacks. The curriculum covers frameworks such as MITRE ATLAS, OWASP Top 10 for LLM Applications, and NIST AI 100-2, and includes labs using tools like garak, PyRIT, and promptfoo. All labs run locally via Docker and require no cloud API keys or external services.

  8. Hacker News AI22

    Show HN: Try an AI agent wallet in the browser – buy a stamp from a bot

    A hosted browser demo lets users get a private BitcoinZ test wallet with free starter coins, message an AI house agent to request a stamp, pay a 50 BTCZ Deal offer, and verify the delivered stamp's SHA-256 fingerprint. The demo takes about five minutes and requires one BitcoinZ block (roughly 2.5 minutes) before delivery; starter coins cannot be withdrawn, and every send pays a 1 BTCZ fee to operator Z-TEXT LLC. Transactions are shielded via zk-SNARKs, though the server can see the test wallet's activity.

  9. Hacker News AI58

    AI advisors debate your business decision in Claude Code

    Roast Room is a Claude Code tool that convenes a council of simulated advisors built from public figures' work to debate a business decision, then delivers a scored verdict and a one-click PDF. It ships with twelve advisors (seven default, five on call), lets users add their own via /newroaster, and runs a local web app showing the advisors around a table. It requires Claude Code and Node.js 20+, and is MIT licensed by AI Automation Society.

  10. Hacker News AI42

    AI Voice Translator

    AI-TRANSLATOR is a synchronous speech and text translator whose translation core emits normalized events to an event bus, which fans them out to any number of independent text sinks (console, WebSocket display page, transcript, Telegram) and voice sinks in parallel. Stage 1 (MVP) is implemented and tested, with Linux as the primary platform, macOS and Windows x86_64 supported for building and running, and a Telegram voice-chat sink built on the libntgcalls media engine. Interfaces may still change before the 1.0 release.

  11. Hacker News AI58

    Lyngvi – A Hardened Sandbox for AI

    Lyngvi is an MIT-licensed, agent-agnostic sandbox for running autonomous coding agents against your own repositories on macOS and Linux via Podman, driven from a JavaFX desktop app or a CLI that share one Java core. It gives each conversation its own container with no default network route (egress only through an allowlisted Squid proxy), a copied working tree with a fresh .git, and secrets held in a gateway sidecar, with changes returned as host-classified patches (apply, hold, reject) committed only to a working branch. It ships reference adapters for Claude Code and OpenCode, supports local model servers through the proxy, and pins its base images by digest.

  12. MarkTechPost71

    Deep Principle Releases Hydrogen-1.0: A 753B Open-Weight Model for Scientific Discovery

    Deep Principle has released Hydrogen-1.0, an MIT-licensed 753B-parameter open-weight model built by post-training Z.ai's GLM-5.3 on chemistry, materials science and life sciences data, laboratory records and agent discovery trajectories, with a 1M-token context and 128K max output. Deep Principle reports it scores 38.3% on FrontierScience-Research versus 33.3% for GPT-6-Astra and 93.0% on GPQA-Diamond, while trailing GPT-6-Astra by 3.33 points on NMR structure elucidation. Weights are on Hugging Face and ModelScope, with BF16 serving tested via SGLang on 8 GPUs, NVFP4 builds for NVIDIA B200/B300 and MXFP4 for AMD MI350X/MI355X, though full datasets and recipes are not released.

  13. Hacker News AI60

    Show HN: Mago, an open source AI video studio, runs locally with Comfy

    Mago Studio is a local-first desktop AI video editor for Windows, macOS and Linux that keeps projects and videos on the user's machine, rendering on their own GPU through ComfyUI or in Mago Cloud when signed in. It offers script-to-video direction with cast, shot lists and storyboards, plus frame-accurate restyling of footage using masks, relighting and character replacement. The code is AGPL-3.0 and designed to be modified by AI agents; local rendering is free, while cloud models are paid and require a Mago account.

  15. Hacker News AI34

    Sunscreen, a stylus, and 16 hours of pair programming with an AI

    A kernel developer describes using Claude to add handwriting recognition to KDE's plasma-keyboard on-screen keyboard, after finding Qt Virtual Keyboard's handwriting mode is gated behind a compile-time flag requiring proprietary engines. Over roughly 15–16 hours of active work he produced four commits (~5,000 lines across 32 files) including a handwriting mode, editing keys, scribble-to-correct, and 79 tests, using PhatWare's GPL-3 WritePad engine (6.75% character error rate) after a self-trained model failed at 82.93%. He credits the AI with speed and fluency across unfamiliar stacks, but argues a human was load-bearing for catching wrong assumptions, insisting on measurement over plausible fixes, and product judgment.

  16. AWS Machine Learning Blog34

    Prepare web content for Amazon Bedrock Knowledge Bases with Crawl4AI

    This post explains when to use the Amazon Bedrock Web Crawler connector versus a custom Crawl4AI-based preparation step that writes Markdown and metadata sidecars to Amazon S3 for ingestion into Amazon Bedrock Knowledge Bases. It walks through the sample AWS CDK workflow—scheduled Fargate crawling, S3 upload, and ingestion job—and covers chunking strategies, metadata filtering for retrieval validation, and responsible AI and security considerations.

  17. Hacker News AI48

    Show HN: aido - Spec-driven, AI Augmented Engineer workflow with Claude Code

    aido is a Claude Code plugin that hands the agent a whole feature—spec, tests, code, commits and pull request—while stopping at each decision that matters for the engineer to approve. It centers every stage on a SPEC.md with numbered acceptance criteria, checks the spec against the repository's CLAUDE.md and AGENTS.md, and offers a fresh-context /aido:verify to confirm the implementation matches what was agreed. Skills cover single-phase and multi-phase features plus utilities for stabilizing existing PRs, resolving migration conflicts and mapping architecture.

Nov 2Mon
  1. The Decoder72

    One brutal Minecraft night scared 50 AI agents into inventing chicken handoff protocols, a Fertilizer Officer, and fishing shifts

    In a three-hour "Civ50" Minecraft experiment, 50 GPT-6.1 Sol agents exchanged about 5,900 messages, lost 22 agents on the first night, and then adopted extreme caution, ration lists, fishing shifts and a written handoff protocol after a tossed chicken was accidentally eaten. In separate Bed Wars and Mindustry matches, GPT agents beat Claude Opus 5.5 6-3 and 6-1 respectively, communicating far more and downloading Mindustry's public source code to refine tactics, while Claude agents misread a block-breaking bug and never searched for game code. The researchers released the Mindustry environment and Multi-Agent Harbor framework as open source, arguing such simulations can surface risky swarm behaviors before they reach production systems.

  2. Hacker News AI38

    Show HN: AgentTrafficCop – Stop AI agents from looping and burning money

    AgentTrafficCop is a runtime circuit breaker for multi-agent systems that validates each handoff against a Pydantic v2 contract, fingerprints payloads with SHA-256, and trips on repeated or A↔B ping-pong payloads and step thresholds. It runs as a standalone FastAPI service with a Python SDK and LangGraph adapter, and is open source under MIT on PyPI, with a free tier covering 5 agents and 10,000 messages per month.

  3. Hacker News AI47

    Mediroute: An open-source AI platform exposing global drug price disparities

    MediRoute is an open-source HealthTech, RegTech and AI Agent platform that compares drug prices across five markets (US, Canada, India, Singapore, UK), checks import legality with cited compliance rules, and offers an AI Medicine Agent, a Drug Shortage Radar and supplier Trust Scores. It cites the example of Imatinib costing $9,800/month in the US versus $208/month from India, and states it is a medicine intelligence platform rather than a pharmacy or marketplace. The MVP covers 8 flagship drugs, 20 bilateral compliance lanes and three languages, with a roadmap toward 100 countries and 100,000 drugs.

  4. Hacker News AI60

    Show HN: Maat – AI agents that can diagnose Ubuntu but can't change it

    Maat is an open-source MCP server and toolkit that lets AI agents diagnose Ubuntu systems from inside a strictly confined snap with read-only interfaces and no network access, proposing fixes as typed plans that a user approves via polkit before execution. It includes maatctl for reviewing and applying plans, a hash-chained audit trail with journal checkpoints, and maat-bench, an open benchmark of deliberately broken Ubuntu machines. The project is a developer preview implemented in Go, with first results from two small local models reported as a preliminary data point rather than a ranking.

  5. Hacker News AI58

    HelpPuff – AI site chat your coding agent deploys to your Cloudflare

    HelpPuff is an open-source, MIT-licensed AI website chat that runs entirely in your own Cloudflare account, with setup done by a coding agent such as Claude Code, Codex or Cursor from a single prompt. It learns your site and files, answers visitors, captures leads, supports live chat handoff, quotes and jobs, and in-chat booking, using Cloudflare Workers, Workers AI, D1, Vectorize, KV and Durable Objects. The default setup fits the Workers Free plan at roughly 300 AI answers a day, and HelpPuff states it has no hosted control plane and receives none of your data.

  6. Hacker News AI65

    TinyContext Guide – How to Add Long-Term Memory to an AI Agent (Step by Step)

    This guide explains how to give an AI agent long-term memory using TinyContext, an open-source memory server that stores facts in a single local SQLite file, by adding save and recall tools and instructing the agent when to use them. It covers setup via MCP in Claude Code, Cursor or Codex, a roughly 60-line Python agent example, and an HTTP API for other languages, plus guidance on what to save and how recall stays within a token budget.

  7. Hacker News AI42

    See what's left of your flat-rate AI subscriptions every time you open a termina

    AIQuota is a single POSIX sh script (requiring only awk and curl) that displays a status band and title-bar summary of how much quota is left on flat-rate AI subscriptions such as Claude, ChatGPT/Codex, Copilot, Freebuff, OpenCode and Gemini, with green/yellow/red dots for the tightest window. It reads each agent's credentials read-only, never refreshes them, has no server or telemetry, and deliberately excludes API keys and metered plans. It is installed via a curl script or manual startup-file line and is tested on Linux and in CI on macOS.

  8. MarkTechPost58

    Meet qwenGPU: Qwen3.5-2B With 45 Compiled GPU Layers That Run CUDA

    qwenGPU is an experimental MIT-licensed project by developer Vixhal that compiles a 4-lane SIMT GPU into 45 untrained layers placed in front of Qwen3.5-2B's own 24 layers, using the model's Gated DeltaNet state as registers, program ROM and global memory. The host compiles CUDA to PTX with clang and feeds it to the model as tokens, and the model writes each launch itself; the developer reports every launch was exact, a reference interpreter matched an NVIDIA Tesla T4 on 49 of 49 kernels, and text drift is a KL of about 7e-4. Reported speed is about 10 to 15 tokens per second on Apple MPS, and no prebuilt checkpoint is published.

  9. MarkTechPost59

    NVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL

    NVIDIA has released Auto Ontology, an Apache 2.0-licensed semantic layer framework that builds a context layer from enterprise metadata so agents can write SQL against certified business definitions. It exposes context through 9 read-only MCP tools plus CLI and API, defaults to nvidia/nemotron-3-nano-30b-a3b with Nemotron embedding and reranking models, and runs via Docker Compose or Kubernetes/Helm with hosted or self-hosted NIM endpoints. NVIDIA reports a 90% cut in ontology creation time in its own testing, but no text-to-SQL accuracy scores are published; a separate eval harness ships without results.

  10. Hacker News AI50

    Show HN: AgentTM – A time-travel debugger for AI coding agents built in Go

    AgentTM v0.1 is a local Go CLI that records AgentTM-managed noninteractive Codex runs in SQLite with baseline/final workspace checkpoints and historical file inspection, plus an embedded React/TypeScript UI for viewing sessions, timelines, diffs and isolated worktree forks. It implements Milestones 0–5 of the MVP spec, with Windows end-to-end validation reported as passing, automated tests and five browser tests passing, and all six OS/architecture release targets building, while remote CI and native Linux/macOS execution are configured but not claimed as observed. Recording requires Git 2.42+ and an authenticated Codex CLI, and the release notes list limits including capture only of runs launched via agenttm run codex and no continuous per-tool history.

  11. Hacker News AI67

    An Illustrated Guide to AI Agents

    This repository hosts the code for the book "An Illustrated Guide to AI Agents" by Maarten Grootendorst and Jay Alammar, published by O'Reilly, which teaches readers to build a TinyAgent from scratch using only LLM calls, with memory, tools, and autonomy. The book spans ten chapters, from introduction to AI agents and large language models through reasoning models, memory, tools, planning, evaluation, multi-agent collaboration, multimodal understanding, and coding agents, and includes more than 300 custom figures. All examples can be run for free in Google Colab using a T4 GPU or locally, with a setup folder providing a quick-start guide.