01Log
Archive
The full log, newest first.
OpenCharts Trading Platform
OpenCharts is an open-source browser-based trading terminal requiring no backend or signup, with charting, drawing tools, indicators, watchlist, depth-of-market, order ticket, and paper trading. It is notable as a self-hosted TradingView alternative with a PineScript transpiler and multi-exchange support.
TDX API Parser
gotdx is a Go library for the TDX market data protocol, covering snapshots, K-lines, intraday data, ticks, F10, financials, and sector queries. It includes address pooling, retries, host speed testing, and a built-in web viewer.
Tiger Open API SDK
The Tiger Brokers OpenAPI Python SDK provides market data, trading, account management, and real-time push via WebSocket. It also includes CLI tools, an MCP server, and AI skills for programmatic and AI-assisted trading.
QAExchange Trading System
qaexchange-rs is a Rust-based high-performance quantitative exchange system and self-developed database for QUANTAXIS. It is production-ready, featuring secondary indexing with under 10-microsecond query latency, ZSTD/LZ4/Snappy compression, asynchronous WAL persistence over 200K ops/s, TLS 1.3, and Prometheus/OpenTelemetry observability.
Algo Trading Engine
the0 is an open-source algorithmic trading execution engine for deploying bots across markets, supporting strategies in Python, TypeScript, Rust, C++, C#, Scala, and Haskell. It provides self-hosted deployment, real-time monitoring, and React dashboards; beta status.
AutoXD Backtesting Framework
autoxd is an A-share backtesting framework for writing T+0 strategies with pandas, featuring simulated real account trading, transaction costs, forward-adjusted prices, and volume-to-turnover conversion. It supports parallel execution via Redis and displays results in publishable page format.
Anthropic Life Sciences Verification Program
Anthropic opens Mythos, Opus, and Sonnet to life science professionals with more permissive biology safeguards — relevant for biotech agent builders needing domain-specific model access.
ACP 1.23.0
ACP 1.23.0 adds a v1 session notice capability (unstable) — a new protocol signal for session lifecycle, useful for client/server implementations tracking session state.
AI Workflow Runtime
DeterminFlow is a production AI workflow runtime for versioned, retryable, recoverable pipelines combining LLMs, scripts, APIs, databases, and human approvals. It isolates each agent node to local context with validated outputs and has been production-tested in AI novel writing.
AI PCB Designer
Konnect is a native KiCAD 10 plugin in Rust that exposes schematic, layout, routing, placement, design-review, and manufacturing tools to Claude and other LLMs via MCP. It bundles over 200 tools and skills for PCB design, aimed at hardware developers.
Website Rebuild Skill
This agent skill captures a read-only mirror of a website, reconstructs it from minified code, and verifies the result with automated diffs. It is designed for any skills-supporting agent and tested across Claude Code and Codex.
App Pattern Builder
Appllama-skills provides agent skills that study top-grossing mobile apps' screens, flows, and UI patterns, then build native-quality mobile screens from that design language. It targets React Native developers who want agents to produce simulator-verified app interfaces.
Agent Cost Dashboard
It creates local work receipts from coding agent session logs, showing tools used, files changed, tests run, and token/time costs. It runs locally with no account or telemetry, making agent activity auditable for developers.
AI Video Cloner
Hypit lets AI agents clone a video as a complete workflow—footage, captions, B-roll, and effects anchored to words rather than seconds—and generate variants. It provides a DSL for AI-driven video production, though its cloning focus is niche.
AI Agent Console
It is an open-source JVM-based multi-platform harness that gives AI agents a browser, terminal, editor, secrets, and 100+ MCP tools. It targets enterprises and research with native multithreading and hot-reload scaling from laptop to supercomputer.
Cindy AI Agent
Cindy is an open-source AI agent that runs locally and combines multiple harnesses, models, and tools to complete real tasks. It initially supports Claude Code and Codex, with cross-platform mobile support planned.
Android Virtual Container
Renjana is an Android virtual container that runs multiple isolated instances of apps with separate storage, Google accounts, and device fingerprints, without root. It uses the Pine dynamic instrumentation framework and targets multi-account and app testing scenarios.
Flectar Mail
Flectar Mail is a lightweight, native email, calendar, and contacts client built in Rust, offering instant startup and low memory use (as little as 20 MB). It targets users who want a fast local-first alternative to web-based mail clients.
Android TV IPTV
OwnTV is a native Android TV IPTV player built with Kotlin and Compose, using libmpv and ExoPlayer to support Xtream, M3U, and Stalker sources. It is player-only, requiring users to supply playlists or portal credentials.
Local Password Manager
Bramble is a local-first password manager that syncs vaults directly between devices without a central server, offering browser, desktop, iOS, and Android apps. It targets privacy-focused users who want to avoid cloud-hosted password storage.
Android Decompiler Front-end
ASC is a fast Android decompiler front-end for agents and mobile researchers, using R8 compiler optimization as a decompiler primitive to avoid heavy indexing and memory use. It targets researchers working with large APKs.
Visual Novel Simulator
Tyranor-Next is an Android multi-engine visual novel simulator that bundles Kirikiri, ONScripter, Tyrano, Artemis, and Siglus runtimes, and supports external Ren'Py and RPG Maker RGSS modules. It provides game library management and emulator launch for niche visual novel gaming.
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Proposes recursively scaling auto-research loops for agent harnesses — targeting unattended coding agents that move beyond supervised code completion.
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Self-retiring on-policy distillation for agentic RL — the distillation schedule adapts and stops when the student stops benefiting, instead of following a fixed plan.
Codex 0.155.0
Codex 0.155 adds experimental /voice conversations, task archiving/deletion, Touch ID verification for MCP requests, and configurable daemon update schedules.
OpenHands 1.20.0
OpenHands 1.20 lets agent profiles select which secrets are available and automations pick saved profiles; Docker conversation runtime settings are now forwarded.
@freyjavalentine.bsky.social: Saw a term calling the act of shitting out Claude code without review and expecting your coworkers to fix it
Bluesky thread coining a term for unreviewed Claude code dumped on coworkers — the 'agent slop' debate continues.
Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS
Show HN: Aclif — agent CLI framework with a single grammar and canonical names across SaaS providers. Ships provider schemas in the binary, no credentials needed for discovery.
GLM 5.3 FlashX
High-speed variant of GLM-5.3-Flash, native multimodal, up to 200 tokens/s.
Qwen3.8 Omni Flash
Alibaba's flash omni variant for low-latency multimodal tasks.
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
ZGCM-1 is a fully open model tuned for math and agentic search, claiming extreme efficiency — worth a look if your agents spend tokens on search-heavy reasoning.
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
HypoEvolve applies genetic selection across multi-agent LLM outputs to evolve scientific hypotheses — an orchestration pattern worth stealing for any agent swarm doing open-ended search.
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
XConf proposes confidence estimation grounded in experiential outcomes rather than model introspection — a calibration approach that could tell agents when to trust their own reasoning before acting.
GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents
GraphEcho dissects where LLM graph agents duplicate structure and lose track of evidence provenance — useful for anyone building retrieval or knowledge-graph agent loops.
AgentTorch Models
AgentTorch implements Large Population Models for differentiable simulation of millions of interacting autonomous agents. It uses autograd to enable learning in agent-based models, targeting collective dynamics like pandemics and climate change.
ESPResSo Package
ESPResSo is a molecular dynamics package for simulating coarse-grained bead-spring models in soft matter research. It is a long-standing research code used in physics, chemistry, and molecular biology.
OpenHPC Integration
OpenHPC provides pre-built components for deploying and managing HPC Linux clusters, including provisioning, resource management, runtimes, and scientific libraries. It is an essential packaging and integration repository for cluster infrastructure.
Ascent Visualization
Ascent is a lightweight in situ visualization and analysis runtime for multi-physics HPC simulations. Developed at LLNL, it enables many-core capable data processing without moving data off-node.
Avogadro Libraries
Avogadro libraries offer 3D rendering, visualization, analysis, and data processing for computational chemistry, molecular modeling, bioinformatics, and materials science. They are key, actively maintained libraries widely used in these fields.
PyOpenCL Integration
PyOpenCL provides Pythonic access to OpenCL for parallel computing on GPUs and CPUs, including arrays and algorithms. It is a foundational, actively maintained integration widely used in scientific computing.