Semantic Skill Space (SSS): Injecting skill embeddings into KV cache for small-model agents to recover skill behavior with lower prompt-context overhead.
☆15Mar 2, 2026Updated 7 months ago
Alternatives and similar repositories for Semantic-skill-space
Users that are interested in Semantic-skill-space are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Local-first persistent memory for AI agents — captures conversations, extracts durable knowledge, resolves conflicts, and reuses relevant…☆18Sep 22, 2026Updated last month
- https://pypi.org/project/intent-suggestions/☆10Sep 6, 2022Updated 4 years ago
- PAROAttn based on SAGEAttn☆11Nov 30, 2025Updated 10 months ago
- A simple script to plot the Roofline model for given HW platforms and applications☆10Mar 17, 2026Updated 7 months ago
- Local-first NotebookLM alternative powered by Nemotron. YouTube transcript, Playwright JS rendering, FTS5 RAG, DDG search, SSE streaming.☆16May 14, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [OSDI 2025] DecDEC: A Systems Approach to Advancing Low‑Bit LLM Quantization☆27Oct 13, 2026Updated 2 weeks ago
- Gloop is a self-modifying, self-replicating CLI AI agent☆15Oct 7, 2026Updated 2 weeks ago
- A systematic empirical study of self-verification strategies in agentic coding harnesses☆29Mar 4, 2026Updated 7 months ago
- Compression primitives for uplink compression in Federated Learning that are compatible with Secure Aggregation.☆11Jul 27, 2022Updated 4 years ago
- ☆12Jun 6, 2026Updated 4 months ago
- Raw speed benchmark traces: Qwen3.8-27B on 4x RTX 3090. llama.cpp GGUF sweeps + 288-point vLLM vs SGLang, NVFP4 vs FP8 matrix.☆13Sep 28, 2026Updated 3 weeks ago
- Stop repeating yourself to Claude.☆14Updated this week
- Agent application/benchmark/workload traces should be placed here.☆20Apr 13, 2026Updated 6 months ago
- ☆16Sep 2, 2020Updated 6 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Echo Mode – A semantic resonance protocol for LLM tone control☆13Oct 7, 2025Updated last year
- AWP | Agentic Web Protocol: Discoverable Websites and APIs, for AI Agents interactions☆18Apr 16, 2026Updated 6 months ago
- ☆12Updated this week
- Local OpenAI-compatible HTTP proxy built on pi's SDK☆16Updated this week
- A modular framework of 22 AI agents, each defined by strict, human-readable YAML architectures. Six classes cover strategic planning, kno…☆13Mar 22, 2026Updated 7 months ago
- PyTorch extension enabling direct access to cuDNN-accelerated C++ convolution functions.☆13Mar 14, 2021Updated 5 years ago
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆13Jul 13, 2026Updated 3 months ago
- ☆10Jun 19, 2025Updated last year
- Offline database schema context for LLM agents. Extract once, serve via MCP — no live DB needed.☆14Mar 16, 2026Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Optimal stopping package for LLM evaluations☆25Sep 13, 2026Updated last month
- A Python research framework and terminal-based IDE (RuleFlow Studio) for modeling, evolving, and analyzing discrete complex systems like …☆17Updated this week
- A direct convolution library targeting ARM multi-core CPUs.☆12Nov 27, 2024Updated last year
- Probe any HTTP server for OpenAI API compliance, with an honest matrix of how the OSS implementations actually behave.☆17Aug 1, 2026Updated 2 months ago
- AI NPC Desktop Platform built with Tauri + SvelteKit + Ollama☆13Feb 15, 2026Updated 8 months ago
- An open source, self-hosted, privacy-focused AI workbench☆80Updated this week
- An experimental desktop client for using Claude Desktop's MCP with Novelcrafter codices.☆11Dec 3, 2024Updated last year
- A simple python-based terminal tool to manage llama.cpp☆13Sep 30, 2025Updated last year
- ☆18Jul 4, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- SearXNG-Crawl4AI is an open-source search and crawling tool based on SearXNG and Crawl4AI, serving as an open-source alternative to Tavil…☆15Oct 27, 2025Updated last year
- BrainStem is a biologically inspired, Real Neuro-Symbolic (RNS-AI) cognitive architecture for lifelong learning. It is designed to learn …☆43Oct 12, 2026Updated 2 weeks ago
- Creating diff that supports wildcard produced by LLMs☆16Sep 18, 2024Updated 2 years ago
- The code for the paper "Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval" (WWW'22, Oral).☆17Mar 8, 2022Updated 4 years ago
- ChungusHub is a local-first, privacy-focused LLM frontend for roleplay.☆41Sep 27, 2026Updated last month
- Privacy-first Chrome MV3 extension that uses Chrome’s on-device Gemini Nano for chat and one-click page summaries—no network calls.☆13Dec 7, 2025Updated 10 months ago
- Truthful local registry and event stream for running coding agents☆12Updated this week