Tag

Apache Maka

Local-first AI agent workspace for authoring, running, and recovering agent executions — records model messages, tool calls, tool results, permission decisions, and termination events in an append-only Runtime Event Log. Provides Desktop (Electron), TUI/CLI, and headless Eval surfaces plus local tools and runtime features for pruning, compaction, and durable recovery.

LoopX

Maintains a local, durable control-plane state that preserves objectives, typed todos, gates, evidence logs, quotas, and verifiable handoffs for long-running AI agent work. Designed to coordinate multi-day agent loops across Codex, Claude Code, Cursor or custom runners while keeping human judgment, auditability, and safe fallbacks explicit.

Cloudflare Computer

Provides a virtual, durable filesystem and pluggable execution runtimes for agents running inside Cloudflare Durable Objects. Offers container, isolate-shell, and isolate-JS backends; preview-stage API with ~10GB Durable Object backing and FUSE-mounted container trade-offs.

Omnigent

Orchestrates, composes, and governs multiple AI agents (Claude Code, Codex, Cursor, Pi, and custom agents) via a meta-harness that enforces policy-based sandboxing, spend caps, and live collaborative sessions. Agent behavior is declared in YAML and can run locally or in managed cloud sandboxes.

firstmate

Routes natural-language requests to a single “first mate” agent that spawns and supervises multiple autonomous crewmates, each running in an isolated git worktree and producing finished PRs, approved local merges, or standalone investigation reports. Key features include visible session backends, disposable worktrees, explicit project modes, optional persistent secondmates, and an event-driven zero-token watcher.

TurboServe: Serving Streaming Video Generation Efficiently and Economically

Serves interactive, long-lived streaming video-generation sessions by jointly scheduling session placement and GPU autoscaling to meet tight per-chunk latency. Combines migration-aware placement, load-driven autoscaling, coalesced chunk processing, GPU–CPU offloading and NCCL GPU–GPU migration; reports ~37% reductions in worst-case per-chunk latency and GPU operating cost.

AFTER

Benchmark for evaluating procedural skill evolution in LLM agents: isolates reusable skill bodies, role-specific work surfaces, and hidden oracle assets to measure whether skill refinements transfer across tasks, roles, and model backbones. Includes 382 workplace tasks, 22 skills, and a controlled evaluation protocol.

NVIDIA GLM-5.2 NVFP4

Provides a pre-quantized NVFP4 checkpoint of GLM-5.2 for long-context reasoning and coding; reduces model footprint so GLM-5.2 can run on multi‑GPU Blackwell nodes and is ready for inference with SGLang and vLLM.

nvidia/Qwen3.6-27B-NVFP4

NVFP4-quantized variant of Qwen3.6-27B that reduces parameter bits from 16 to 4, cutting disk and GPU memory requirements by ~2.5× while keeping comparable benchmark accuracy; ready for vLLM-based inference on NVIDIA hardware and supports long, multimodal contexts.

Ornith-1.0-397B

Provides an open-source Mixture-of-Experts coding LLM (397B) optimized for agentic, tool-enabled coding workflows with a 262,144-token context window, OpenAI-compatible API, serving recipes (vLLM/SGLang), and published coding-benchmark results.

Qwopus-3.6-35B-A3B-Coder-MTP-GGUF

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.

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Predicts per-request MoE expert footprints from prefill activations and routes decode requests to workers that maximize expert-locality, lowering decode latency by combining offline K-means partitioning with online locality-band routing and a KV-block–coindexed signature cache.