Compresses an entire document collection into 16 query-dependent memory tokens for a frozen LLM. It retrieves useful clues across long histories while keeping the model’s input length fixed.
Measures how autonomous AI agents learn via long-horizon, feedback-rich executable tasks; publishes 51 public tasks from a 134-task suite and provides SForge, a two-container evaluation harness for iterative 12+ hour runs to track learning trajectories.
Checks AI agent skills for quality and safety, then compares task outcomes with and without a skill to measure its actual impact. Its pipeline covers validation, overlap detection, and live agent evaluation.
Routes agent requests across hosted, bring-your-own-key, and local models through one OpenAI-compatible API. It can also use production traces to optimize routing or train a specialized model.
Provides a GGUF-quantized local build of Ornith-1.0's 9B dense model for offline inference and terminal-focused coding agents. Supports OpenAI-compatible tool-calling, a 256K context window, and runs via llama.cpp or Ollama on a single high-memory GPU.
Keeps important decisions, tasks, and reference material in local Markdown notes that compatible AI agents can reuse across sessions. It does not archive entire chats, and retrieval relies on local keyword matching.
Thinking-off fine-tune for coding-agent workflows that prioritizes fast next-step decisions, lower token usage and stable multi-turn tool calling. Highlights: MoE 35B base, MTP speculative decoding, SWE-bench 62.4% (300 cases). Best for local agent loops and automated debug cycles; requires disciplined harnessing and schema consistency.
Matches detection paradigms to four stratified attack-surface layers of AI agents — infrastructure, protocol/tool, agent behavior, and model — and presents AI-Infra-Guard: an open-source red-teaming framework with rule-based infra scanning, LLM-driven audits of MCP servers and skill packages, and a jailbreak/attack-operator harness.
Indexes mixed-format folders locally into a zero-config, Elasticsearch-compatible search engine offering keyword, semantic, vector and hybrid retrieval. Embeds on ingest, provides per-agent namespaced memory and AST-aware code indexing in a single static binary with no external embedding key.
Provides quantized GGUF weights and configs for Agents‑A1 — a 35B Mixture-of-Experts agent trained for long-horizon, tool-enabled reasoning; supports 262K-context serving and runtimes like vLLM and SGLang.
Coordinates AI agents you already use by routing tasks according to their capabilities, sharing context, and combining results. It connects agents through local integrations, making it useful for work that spans tools and workflows.
Evaluates how long-term memory in LLM agents amplifies sycophantic behavior and when memory should or should not influence decisions. Provides five targeted tasks, 1,550 standardized samples, an evaluation pipeline, and baseline adapters to test memory use, conflicts, scope, updates, and personalization.