Stop building your AI stack from 40 open tabs.

xerj-org 19.1k · today

One Rust binary for agent search: BM25, vector and hybrid search over code, docs, logs and PDFs, an Elasticsearch-compatible API, MCP, and Query-1, which answers by running programs over facts.

Tencent 36.6k · 3 days ago

Tencent's enterprise knowledge platform: one set of document bases served three ways, as RAG search, a reasoning agent with sandboxed skills, and a self-maintaining LLM wiki.

TencentCloud 30.5k · 2 days ago

Tencent's team memory hub for agents: an API proxy turns conversations, docs and code into shared chat memory, skills, an LLM wiki and a code graph, reused across agents.

facebookresearch 223 · yesterday

Meta's benchmark for open-ended bug hunting: given a real repository and no hints, an agent must find and fix as many bugs as it can. Scored as a micro-average of bugs resolved.

openqodex 1.1k · yesterday

Local pre-push code review for coding agents: deterministic scanners (gitleaks, semgrep) plus separate Claude Code/Codex reviewer sessions, with a push gate. No account or key of its own.

anomalyco 224.8k · today

The open-source terminal coding agent: TUI, desktop app and server, provider-agnostic across 75+ model providers including local models, with LSP integration and plugins.

elstongun 879 · 4 days ago

Single Rust binary that turns JSONL, CSV, SQLite or any DB export into a ranked full-text index, giving agents short cited answer cards (~450 tokens) at any dataset size.

ifixai-ai 43.5k · 4 days ago

Independent auditor for AI agents: drops the agent into a simulation of your business, sends realistic requests, and scores operational alignment, permissions and red-team risk in ~2 minutes.

HelixDB 2.1k · yesterday

HelixDB's ontology builder: connect databases, tools and docs, let an agent draft an ontology, and load it all into HelixDB as one explorable, queryable graph with provenance.

google-research 22.8k · 4 days ago

Google Research's recursive harnessing framework: an agent refines its own harness (prompts, tools, memory, skills) per task via Propose–Probe–Compose, with model weights fixed.

Graphicle-AI 509 · yesterday

One Rust program giving coding agents a code graph plus memory of docs, decisions and past sessions, served over MCP to Claude Code, Codex, Cursor and VS Code.

liliang-cn 475 · yesterday

Agent memory plus a knowledge graph with ontology constraints in one SQLite file: pure Go, no server, no embedding model required. Plugins for Claude Code, Codex, dsh and Obsidian.

wheresryan22 25.2k · 19 days ago

Agent skill that explains an idea by inventing a physical machine whose working is the concept, then builds it as an interactive isometric SVG, optionally with WebGL effects.

tomtomsatnav 103 · 2 days ago

Read-only live monitor for Claude Code: a streaming graph of sessions, subagents, tokens, cost, file conflicts and alerts, as plugin, TUI and MCP server. Ships the AOS-1 spec.

trymirai 3.2k · yesterday

Rust inference engine for on-device AI on Apple Silicon (Metal, unified memory) with Swift, Python and TS bindings, OpenAI-compatible server and a TypeSafe System One decision-model API.

awlevin 1.3k · 1 months ago

macOS computer-use loop at ~$0.0002/step: OCR + accessibility tree read the screen, a TypeSafe classifier picks the next action, code clicks; an LLM writes only free text.

Niko1221 40.6k · yesterday

Hybrid GPU/CPU MoE engine that runs Qwen3.8-Flash-Next and DeepSeek V4.1 on consumer cards: hot experts cached in VRAM, rest computed in RAM, MTP drafting, local OpenAI/Anthropic API.

morluto 434.3k · yesterday

Reverse Engineer Anything: one MCP server plus CLI giving coding agents evidence-backed analysis of native binaries, JS/Electron apps, .NET assemblies and websites via Hopper, Ghidra or IDA.

realZachi 1.3k · 1 months ago

Postgres extension for plain-language WHERE clauses: jev(row,'the customer is angry') filters, ranks and classifies rows via TypeSafe's Jev decision model. No embeddings, no vector column.

aerovato 500 · yesterday

Context engine for coding agents: each session consults, then updates, a Markdown brain of specs, decisions, standards and lessons — private, team-shared via Git, and per-user. No embeddings.

mvschwarz 8.7k · yesterday

Define a team of Claude Code, Codex and Pi agents in YAML and boot it with one command: persistent tmux-backed seats with roles, shared context and owned work, steered via a lead agent.

CopilotKit 6.4k · yesterday

CopilotKit template for always-on AI coworkers ('Dots'): each gets a role, tools and its own computer, works in chat, calls and Slack, and saves approved drafts into editable Spaces.

TencentCloud 11.7k · yesterday

Tencent Cloud's self-hosted, multi-user AI assistant: per-user expert agents, AgentTeams, memory, RAG and connectors, served as one process to a web dashboard, CLI and 8+ IM channels.

project-minigraf 225 · yesterday

Embedded single-file graph database in Rust with Datalog queries and bi-temporal time travel — 'SQLite for connected data with history' — running native, WASM, mobile and in the browser.

dosco 3.2k · 5 days ago

Go compiler + runtime exposing databases, warehouses, files and code as one governed GraphQL + MCP graph for agents — catalog-first discovery, allow-lists, built-in agent, standing watches.

tester-army 13.3k · yesterday

Agentic e2e testing for web and mobile: describe a goal, an agent drives the app, locators assert the result. Verified agent steps replay with zero model calls until the UI changes.

mksglu 33.6k · yesterday

Local plugin for 10 coding agents that runs tool calls in a sandbox, indexes full output in SQLite FTS5 and returns only what the agent asks for — ~99% fewer bytes in context, zero telemetry.

uber 2.1k · 6 days ago

Uber's Agentic AI Detection and Response: inventory AI tools on endpoints, capture Claude Code/Cursor/Codex telemetry, and flag risky sessions with a two-tier detector; ships ADR-Bench (300+ tasks).

lexmount 22.7k · yesterday

Rust headless browser for AI agents on Servo/Stylo components: fetch pages as Markdown or a semantic tree, automate via CDP, WebDriver or BiDi — about 13% of Chrome's memory per task.

raphaelmansuy 136 · 5 days ago

Markdown to knowledge graph with an ontology you write: a small local decision model answers closed yes/no questions per candidate, and your cutoff keeps, queues for review or drops each link.

datalab-to 1.3k · 15 days ago

Datalab's 9B vision model that extracts JSON matching your schema from PDFs and images in one pass — schema-constrained decoding, multi-page values, vLLM or HF inference, Schema Studio.

thu-nics 770 · 9 days ago

Cache-to-Cache (ICLR'26): LLMs talk by projecting and fusing each other's KV-caches instead of generating text — higher accuracy than text relay at ~2x lower latency. Fuser weights on HF.

NVIDIA 24.4k · 2 days ago

NVIDIA's security scanner for agent skills: 71 patterns across 17 categories — prompt injection, exfiltration, supply chain, MCP tool poisoning — static plus optional LLM pass, SARIF output.

FalkorDB 10.5k · yesterday

Low-latency, multi-tenant property graph database that runs queries as sparse-matrix linear algebra (GraphBLAS); OpenCypher over the Redis protocol, built for GraphRAG and agent memory.

strands-agents 9.1k · yesterday

Strands Agents: open-source Python and TypeScript SDK for building and running agent harnesses in your process — model-agnostic, with lifecycle controls, hooks, MCP, multi-agent and tracing.

strands-labs 763 · 2 days ago

Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.