Search

BCP 1979 Daily Office: readings, psalms, and collects for any date — light by default, with optional full Bible text.

Retrieval-grounded question answering for public agencies: answers only from an operator-supplied corpus, cites its sources, refuses cleanly when it has none.

Convierte videos en artículos de blog en Markdown mediante IA

Attribute the pytest failures that leave no trace: internal errors, and xdist worker deaths, stalls and collection mismatches

Metal-native embedding backend for manicule, on Apple Silicon.

Official SIFEN geographic location catalogs for Django: departments, districts, cities, and neighborhoods in Paraguay.

Inspect extension: isolate and decompose LLM-grader (judge) variance in a benchmark score, and give a stopping rule for how many grader repeats are needed.

High-performance Async Rate Limiting, Circuit Breaking & Resilience Orchestration for LLM & API Pipelines

Pre-flight connectivity checks for the n8n + Ollama training stack.

Capture the literal HTTP request/response of every LLM provider call (by patching globalThis.fetch) and show them in a Wire Trace session tab

YYLO Ledger: Git-native task management with safe per-task Markdown storage

Re-registers the dormant ACP_BACKEND_CLAUDE seam so KiroCrew runs on Claude Code

A lightweight checkpoint layer for LLM outputs — Path B: self-reported confidence with reconsideration retries.

DSH LLM API pool manager: multi-subscription opencode go management with official usage/balance (pure API key), usage-based hot-switch routing, and a settings-page UI. 多 LLM API 订阅池管理:官方余额/用量查询 + 用量感知热切换 + 设置页图形化管理。

Per-residue structural context (microenvironment) from AlphaFold: relative solvent accessibility (RSA), secondary structure, contacts, pLDDT, and per-residue protein-language-model embeddings.

OGPT - AI coding assistant for the terminal with a built-in local engine

Silence-aware chunking and OpenAI transcription for long audio.

Superagent Replacement

ICE: Intervention-Consistent Explanation Evaluation for LLMs

Provider-neutral LLM service interface for the DeepSeek Harness