Skip to content

Showing all 22

Research

22 records filed under this subject, newest first, each with what it is, what it cost and where the builder got stuck.

Records

22
148JeffA 0.8B open model that answers first and hands the query to a large model only when its own confidence falls below a threshold.ClaudeSep 2026Sep 2026146LayaSmall encoder models that read a document once and return a probability for every option of every typed question, with nothing generated and a router that picks the checkpoint by script.ClaudeGitHub CopilotSep 2026Sep 2026145KevA family of small models that read one document and answer a typed set of questions with a probability for every option. No text is generated.DevinSep 2026Sep 2026143AntOmniEvoA Python framework that runs an evolution loop over a directory of your files: a coding agent rewrites them from the failure trajectories of the previous candidate, parent and child are scored on the same training batch, and only an improvement that clears a threshold is re-scored on the validation set and kept.ClaudeClaude CodeSep 2026Sep 2026141ForbricA Minecraft mod loader that runs Fabric, Forge and NeoForge mods in the same instance.ClaudeSep 2026Sep 2026134agent-memoryA long-term memory runtime for AI agents that keeps plain Markdown files as the single source of truth, ranks them locally without calling a model, answers recall with file paths the agent opens one level at a time, writes at conversation boundaries rather than on the agent’s initiative, and runs an independent sleep-time layer that may add and update on its own but can only ever file a deletion as a proposal — one store shared by Claude Code, Codex CLI and Hermes, with no API key.ClaudeClaude CodeCodexSep 2026Sep 2026131EaselAn open-source content workbench for social media creators: one agent runs the whole loop — aggregate the hot lists, plan a topic, generate the copy, the cards, the voice and the video, publish the finished file to an account that is already logged in on seven Chinese platforms, then read the numbers back into the account profile that shaped the next round.ClaudeClaude CodeGemini+3Aug 2026Aug 2026128sepiaA portable de-AI writing skill: four operations over one canonical rules file, narrative architecture repaired before word choice on fiction, a thin rule file matched to the venue on professional prose, and every rule labelled as measured, consulted or the project’s own inference.ClaudeClaude CodeCodex+4Aug 2026Aug 2026127LemmalogA Rust Datalog engine that treats agent memory as a deductive database, not a bigger vector store: facts asserted at the extraction boundary, stratified rules deriving closures and temporal views, provenance back to the source episode on every derived fact, and views maintained one epoch at a time — served to Claude Code and Kimi CLI as twelve MCP tools.ClaudeClaude CodeGPTAug 2026Aug 2026119DesktopFlyA 3D fruit fly that lives on a macOS desktop, driven by a spiking simulation built from the FlyWire brain wiring and the MaleCNS brain-to-leg network, with a live brain window you can click to stimulate a region.ClaudeAug 2026Aug 2026092SimpleEnglishAn agent skill that makes a model write plain English under ASD-STE100 Simplified Technical English, the controlled language aerospace has used since 1983, with layman-readable as the default and STE-strict on request.ClaudeJul 2026Jul 2026082The Fable MethodHow Claude Fable 5 worked, written down as four skills any model can run, plus the adversarial eval that keeps them honest: fourteen trap fixtures, blind judges that diff and execute rather than read reports, and fifteen rounds of results with the failures and the nulls left in.ClaudeClaude CodeJul 2026Jul 2026080EngramA learning engine that installs into a coding agent: a curriculum architect breaks a topic into a first-principles concept map, a tutor makes you predict, attempt and explain before it explains, a blind assessor grades your verbatim free recall and writes a receipt for every verdict, and a deterministic FSRS-4.5 core in one Python file decides when each concept comes back, with explorable HTML built only for the concepts whose content rewards manipulation.ClaudeClaude CodeCodex+2Jul 2026Jul 2026078ColibrìAn inference engine in pure C with no engine dependencies that treats storage, RAM and VRAM as one hierarchy, so 744B to 2.8T-parameter mixture-of-experts models run on hardware people already own.ClaudeCodexJul 2026Jul 2026068book-to-skillA converter that reads a document (one file, a folder, a glob or a list of paths, in PDF, EPUB, DOCX, HTML, RTF, MOBI or plain text) and writes an agent skill: a core file of mental models with a chapter index, one file per chapter that loads only when a question touches it, and a glossary, a patterns file and a cheatsheet beside them.ClaudeClaude CodeCursor+2May 2026May 2026059Blatant-WhyA protein-design campaign kit for Claude Code: prompt-defined agents write the model inputs, submit them to BoltzGen, Protenix or PXDesign on whatever GPU you have, and rank what comes back with a published interface score.Claude CodeClaudeMar 2026Mar 2026058LeanCTXA local layer that sits beside a coding agent and decides what reaches the model: file reads are compressed and cached, command output is compressed by per-command rules, session findings persist across chats, and a local proxy rewrites each request without breaking the provider’s prompt cache — with a savings ledger, a budget and a dashboard for what it measured.ClaudeClaude CodeCursor+2Mar 2026Mar 2026050autoresearchGive an AI agent an LLM training script, a fixed five-minute budget and no supervision. Then see what it found while you slept.Claude CodeCodexMar 2026Mar 2026049vphone-cliRuns iOS inside Apple’s Virtualization.framework on a physical Apple Silicon Mac, with a graphical window, pre-patched firmware, VM cloning and an optional local HTTP and WebSocket automation API.ClaudeFeb 2026Feb 2026034MiroFishA prediction engine that builds a parallel world of hundreds of AI agents out of a document you upload, then runs it forward to see what happens next.ClaudeGeminiNov 2025Nov 2025017BettaFishA public-opinion analysis system in which several kinds of research agent are made to argue with each other on purpose, so the output is not one model’s opinion written up at length.Jul 2024Jul 2024015SWE-agentA research project that argued the model was never the bottleneck; the interface was.GPTClaudeApr 2024Apr 2024

Adjacent subjects

Categories