Stop building your AI stack from 40 open tabs.

supercorp-ai 56 · today

Code quality and coverage for coding agents: a Rust CLI that scores files with Jev, runs your existing test command, and turns uncovered paths into small actionable targets.

githubnext 380 · yesterday

GitHub Next's local Jev bridge: a Bun/TypeScript POST /v1/systemone that translates typed decision questions into prompts for DiffusionGemma behind any OpenAI-compatible endpoint.

browser-use 8.3k · yesterday

Browser Use's speed experiment: Jev picks the operation and the target element from an indexed action space in one request, and a small LLM writes text only when typing is needed.

jarrodwatts 1.2k · 2 days ago

One AI trade decision every Monad block: Jev reads the Kuru MON-USDC book every ~300ms, answers buy or sell, and the bot reposts a post-only limit order to earn the spread.

tamaratran 4.2k · yesterday

Claude Code plugin and npm library that replaces compaction summaries with Jev decisions: every tool call and result is scored, stale ones dropped or truncated, everything kept stays verbatim.

jaredpalmer 492 · today

Open reproduction of TypeSafe's Jev: a LoRA + readout head on Qwen that answers many typed questions about one document in a single prefill pass, returning calibrated probabilities.

max-sixty 8.1k · today

wt: the Rust git-worktree CLI built for parallel AI agents - worktrees addressed by branch name, `wt switch -c -x claude feat` creates one and starts an agent, plus hooks, list-with-status and merge.

NVlabs 2.4k · today

NVIDIA's Pi extension with four auto-research-discovered efficiency mechanisms - action fusion, observation packing, evidence-preserving log reduction, online context compaction - all opt-in.

ayghri 48.6k · today

48k-star skill that stops coding agents burying the answer: lead with the next action, number steps, cap lists at 5, no preamble/recap/closers. ADHD-friendly, but it's for everyone.

jordan-gibbs 3.5k · 7 days ago

Deep-research harness for Claude Code: a 16-step, tier-adaptive pipeline with adversarial critics, cite-checking and 250+ sources per run, every source kept in a persistent markdown+SQLite vault.

ZJU-REAL 1.1k · today

ZJU's self-hosted enterprise AgentOS on AgentScope 2.0: domain ontology as a control plane for agents, plus RAG, sub-agents, MCP, skills, sandbox, memory and approval-gated self-evolution.

bilawalsidhu 38.5k · 2 days ago

Browser 'spy-satellite' simulator on real open data: live aircraft, ships, satellites, quakes and public cams on a photorealistic 3D globe, voice-driven by a realtime AI agent.

MichaelS1011 41 · today

Capability-based WASM sandbox for MCP tools and agent-generated code: wasmtime + WASI with fuel, memory, time and I/O caps per run, sub-ms warm execution and signed (JCS/ES256) execution records.

sopaco 3k · 5 days ago

Litho: a Rust, DeepWiki-style doc generator that turns any codebase into C4-model architecture docs - context, container, component and code-level pages with diagrams - via any LLM.

ChesterRa 1.2k · today

Group-chat orchestration for coding agents: Claude Code, Codex, ChatGPT Web and others in one durable group with an append-only ledger, read receipts, and Web/IM/mobile ops.

Tencent 4.8k · today

Tencent's team-level agent config manager: skills, rules, agents, hooks, MCP and env live in a shared git repo and sync into Claude Code, Codex, Cursor, CodeBuddy, OpenCode and more on every session.

weave-os 4.5k · today

Weave's Go model router: drop-in proxy speaking Anthropic, OpenAI and Gemini APIs that scores each request with an on-box ONNX embedder (Avengers-Pro clusters) and routes to the cheapest fit model.

redhat-et 2.3k · today

Red Hat's 'ripgrep of AI context': a zero-dependency C++23 CLI + MCP that hands a coding agent a ranked call graph — what to touch, blast radius, tests to run — with no index server.

Human-Agent-Society 3.7k · today

Continual-learning infra for self-improving agents: serve traffic (OpenAI/Anthropic-compatible), match feedback to runs, train weights via Slime/SGLang or evolve the harness, ship versioned updates.

Continuum-AI-Corp 256 · yesterday

Time travel for coding agents: a local proxy records any run (Claude Code, Codex, SDKs, even TLS-only harnesses), replays it byte-for-byte offline, and forks from any step onto a different model.

okf-memory 700 · today

Git-native agent memory on Google's OKF v0.2: Markdown+YAML concepts in knowledge/, a zero-dep Go CLI/MCP with <300µs BM25 search, provenance and trust tiers.

hydra-db 3.2k · 1 months ago

Object-store-native distributed graph DB in Rust: graph on SlateDB over S3, snapshot-consistent OpenCypher, GraphBLAS traversal, Neo4j Bolt 5.x compatibility, disaggregated data nodes and indexers.

HarnessRouter 1.5k · today

Self-hosted Apache-2.0 reference implementation of the Unified Harness Protocol: one OpenAI-Responses-style API running Codex, Claude Code, Hermes, Pi and DSH with sessions, streaming, files, traces.

Atomburstofficial 146 · today

Read-only inventory of every AI agent, MCP server, hook, plugin and AI extension on a machine: npx geiger-scan labels what can execute code, hold secrets or reach the filesystem, with evidence.

FlowiseAI 55.5k · 1 months ago

The 55k-star visual builder for LLM apps and agents — drag-and-drop chatflows and Agentflows, hundreds of nodes, self-hostable Node.js. Now ARCHIVED upstream (see 'Future of Flowise').

timgordontg 280 · yesterday

Local SQLite episodic memory shared across Antigravity, Claude Code, Cursor, Windsurf and Codex: hooks/MCP capture decisions, FTS5+model2vec hybrid recall reloads ~1k tokens per session.

jucelioalencar 20 · 6 days ago

Legible persistent agent memory: records observable execution events, consolidates only validated knowledge and explains every relation — MCP server on PostgreSQL 17 with a web explorer.

iOfficeAI 30.8k · 3 days ago

Office suite built for AI agents: one binary, no Office install, creates, reads and edits Word, Excel and PowerPoint, and renders them to HTML/PNG so the agent can see what it made. Ships as a skill.

Tencent 1.6k · 3 days ago

Tencent WeChat's universal multimodal embedding family (2B/4B/9B): one vector space for text, images, video, visual documents and interleaved inputs, with Matryoshka dimensions from 64 to 4096.

ovg-project 1.4k · yesterday

Virtualized, elastic KV cache for LLM serving on shared GPUs: reserve virtual memory, back it with physical GPU memory only when used — vLLM and SGLang, with a memory-limit CLI, router and sleep mode.

vllm-project 288 · today

Rust gateway that gives vLLM a stateful, OpenAI-compatible Responses API: server-side conversation state, server-side tool loops, SSE and WebSocket streaming, background runs — Codex-ready.

CopilotKit 5.2k · today

CopilotKit's self-hosted AI coworkers: each gets its own computer — a real browser with logins, files, granted tools — with every action decided before it runs and recorded after. Any AG-UI agent.

ralforion 211 · yesterday

Browser ontology workbench for OWL and SKOS on Streamlit + rdflib: OWL-RL reasoning, 22 SKOS checks, SPARQL console, bulk edits, gist starters and a vis-network graph — no Java, no Protégé.

NVIDIA-NeMo 1.1k · today

Molt: NVIDIA's agentic-first RL framework in ~9K lines — Ray for placement, vLLM for rollout, AutoModel + FSDP2 for training — fully async, multimodal, multi-turn, scaling to 1T-class MoE.

arcboxlabs 5.7k · yesterday

Open-source container and VM runtime for macOS in pure Rust: drop-in Docker engine, sub-100ms agent sandboxes (`abctl claude`), full Linux VMs and throwaway macOS guests on one daemon.

bingreeky 487 · 23 days ago

JIT-Agent: a meta-agent that writes a task-specific harness on the fly — memory, planning, action and capability modules emitted as code — and revises it from traces at test time.