Stop building your AI stack from 40 open tabs.

lobehub 80.9k · today

LobeChat's 80k-star pivot: from chat UI to 'Chief Agent Operator' — hire, schedule and supervise a team of agents running 7×24, self-hosted via Docker or Vercel, plugin ecosystem carried over.

getagentseal 9k · today

Local-first cost ledger for AI coding: reads the session files 36 tools already write and breaks every token and dollar down by task, model, project. TUI, web, desktop, menubar — no proxy, no keys.

rohitg00 25.9k · yesterday

Persistent memory for coding agents on the iii engine: MCP server with 53 tools, 12 auto-capture hooks, hybrid search + knowledge graph, zero external DBs. Claims 95% R@5 and 92% token cuts.

santifer 62k · today

Turns your coding CLI into a job-search command center: scans Greenhouse/Ashby/Lever, scores listings A-F into a 1-5 rubric, tailors ATS-ready CVs, tracks applications. Claude Code, Codex, OpenCode+.

memvid 16.1k · 14 days ago

Single-file memory layer for agents: data, embeddings, index and metadata in one portable .mv2 — append-only Smart Frames, time-travel queries, sub-5ms recall, no server. Rust core, Node/Python SDKs.

rtk-ai 73.7k · today

Rust CLI proxy compressing dev-command output 60-90% before your agent reads it — git, tests, linters, docker, 100+ commands; hooks auto-rewrite bash calls. Single binary, <10ms overhead.

msitarzewski 137.3k · 5 days ago

137k-star roster of specialist agent personas — engineering, design, marketing and ops divisions — installable into Claude Code, Cursor, Codex and 13+ tools via scripts or a native desktop app.

alinaqi 704 · 14 days ago

Claude Code config pack + optional local harness: TDD-enforcing hooks, 67 skills, quality gates, persistent memory — plus a dashboard routing each task across 13 models by cost-aware blast score.

mindfold-ai 13.2k · today

Spec, task and memory layer that lives in your repo: .trellis/ holds conventions, PRDs and journals, auto-injected each session — one workflow across 20 coding-agent platforms.

aden-hive 10.8k · 2 months ago

YC-backed multi-agent harness for production: state an objective and the runtime compiles a graph DAG of specialized agents — role-based memory, crash recovery, cost limits, human-in-the-loop.

1jehuang 12.7k · today

Rust coding-agent harness built for footprint: ~28MB per session vs 140-390MB for Codex/Claude Code, instant boot, optional local embeddings — made for running many sessions in parallel.

secureagentics 460 · 4 days ago

Runtime security for AI agents: watches actions AND reasoning traces to catch prompt injection, tool poisoning and out-of-remit behavior — blocking before the action lands. SDKs + Claude Code plugin.

Zipstack 6.9k · yesterday

LLM-driven platform turning unstructured documents into structured data: a no-code Prompt Studio to define extractions, then deploy as APIs or ETL pipelines. Self-hosted, AGPL + enterprise.

codejunkie99 144 · 5 days ago

Graph engineering as a Claude skill: SEU's 9-stage knowledge-graph course (translated) plus task-graph orchestration patterns — with a teaching mode and nine paste-ready /kg workflows.

calesthio 10.8k · 2 months ago

Self-hosted OSINT terminal: 27 open feeds — satellite fires, flights, radiation, sanctions, markets, conflict data — polled in parallel onto one Jarvis-style dashboard. LLM turns it two-way.

shiyu-coder 34.4k · 3 months ago

The first open foundation model for financial candlesticks: trained on K-lines from 45 global exchanges, AAAI 2026, weights on Hugging Face with fine-tuning scripts for your own tasks.

MatthewZMD 915 · 2 days ago

Aider woven into Emacs: AI pair programming with intelligent model selection, Ediff for reviewing AI changes, and file management that stays true to Emacs workflows. MELPA-packaged.

HKUDS 7.1k · yesterday

HKUDS's skill lifecycle layer for agents: retrieve the right skill per task, evaluate which ones actually work from real outcomes, share across agents and teammates, evolve with every run.

plasma-ai 614 · yesterday

Hierarchical agent loops: nodes iterate toward a goal in their own git worktree and spawn children for subtasks — the tree grows to fit the problem. Hard caps, SQLite run log, live TUI.

huggingface 2.1k · yesterday

Hugging Face's Python port of Pi's minimalist coding agent: a real terminal agent with TUI, sessions and skills — built to be READ, with a clean brain/environment/frontend separation.

marcelroed 3.5k · 2 days ago

Tokenization at GB/s: ~1000x faster than HuggingFace tokenizers with drop-in compatibility modes for HF and tiktoken — Rust reading your files directly. pip install gigatoken.

ogulcancelik 21k · 2 days ago

Agent multiplexer for your terminal: every Claude Code/Codex session in real panes — blocked/working/done at a glance, detach and reattach over SSH, plus a socket API agents drive themselves.

neural-maze 183 · 4 days ago

Runnable course: a production OCR pipeline on Kubernetes — Rust ingestion, Qwen 3.5 (4B) served by vLLM at 1.86 pages/s, Redis queues, KEDA autoscaling. Deploy it on AKS/GKE, not a notebook.

openai 91 · 4 days ago

OpenAI's GitHub Action for CI hardening: bounded egress filtering and runner lockdown — the fence that keeps supply-chain attacks out and your CI-resident coding agent in.

VectifyAI 34.8k · yesterday

Vectorless, reasoning-based RAG — builds a hierarchical tree index from long documents so an LLM retrieves by relevance instead of similarity. No chunking, no embeddings, no vector DB.

matrixorigin 472 · 29 days ago

Rust memory layer for AI agents with Git-style version control — snapshot, branch, merge and rollback over MatrixOne's copy-on-write engine, plus hybrid vector + full-text retrieval.

lightpanda-io 32.7k · yesterday

From-scratch headless browser in Zig for AI agents and automation — CDP-compatible (Puppeteer/Playwright connect as-is) at ~9x the speed and ~16x less memory than headless Chrome.

pinchtab 9.7k · 2 days ago

Small Go HTTP/MCP server that gives AI agents direct control over Chrome — stealth CDP injection, multi-instance orchestration and a real-time dashboard. Local-first, single binary.

ruvnet 66.2k · yesterday

ruvnet's 65k-star 'agent meta-harness': multi-agent swarms, adaptive memory and RAG layered over Claude Code, Codex and Hermes — npx ruflo, a UI beta, and a sprawling plugin ecosystem.

nexu-io 8k · 14 days ago

The agentic HTML editor: your local coding-agent CLI (9 auto-detected, zero API keys) writes magazine pages, decks, posters and tweet cards via 75 skills — sandboxed preview, 1-click export.

opendataloader-project 27.9k · yesterday

Deterministic PDF parser for AI pipelines: #1 extraction accuracy (0.907) on its public bench, bounding boxes on every element, 0.015s/page — plus the first open PDF auto-tagging for accessibility.

opensandbox-group 12.2k · yesterday

CNCF-landscape sandbox platform for AI agents: multi-language SDKs, unified API, CLI and MCP over Docker/Kubernetes runtimes — coding agents, GUI agents, evals and RL training.

SWE-agent 6.1k · 5 days ago

The 100-line agent from the SWE-bench team: >74% on SWE-bench Verified with no tools but bash, no config sprawl — the reference minimal harness, adopted by Meta, NVIDIA and Ramp.

moorcheh-ai 1.7k · 4 days ago

Companion memory agent for 20+ coding agents, built on Moorcheh — its own information-theoretic engine, no third-party vector DB to manage. Runs local (Docker + Ollama, keyless) or on their cloud.

deeplethe 2.7k · 6 days ago

fork() for agent microVMs: children fork copy-on-write from a warm Firecracker parent — 100 KVM-isolated VMs in ~100ms, live-VM branching in ~56ms, portable snapshots from a hub.

activeloopai 1.5k · 4 days ago

Activeloop's shared brain for agent TEAMS: traces from Claude Code, Codex, Cursor & co become reusable skills every teammate's agent can execute — cloud-backed, 25% cheaper on LoCoMo.