StackMap
Subscribe

Stop building your AI stack from 40 open tabs.

A curated map of open-source AI & agent tools. Every connection is a typed, human-reviewed relationship — with the why written down. How we curate →

486 repos · 24 topics · curated by ShipWithAI · new: TokenEconomizer, orca, onyx →

Build a coding agentThe open-source RAG stack
486 repos
TokenEconomizer logo
4
microsoft avatarmicrosoft 7.8k · today
TokenEconomizer

Microsoft Research plugin that cuts coding-agent cost 18-31% on SWE-Bench by learning repo facts from past sessions, pruning unused tools and redirecting stuck failure loops — no agent changes.

coding
→ pairs well with rtk, codeburn
orca logo
6
stablyai avatarstablyai 129.7k · today
orca

Desktop agent orchestrator for running Claude Code, Codex and other coding agents in parallel, each in its own worktree — chat or terminal, diff review, git/PR flow, remote runtimes and a mobile app.

codingorchestration
→ pairs well with opencode, agent-orchestrator
onyx logo
5
onyx-dot-app avataronyx-dot-app 33.5k · today
onyx

Self-hosted context layer and AI chat for teams: indexes 50+ workplace apps with permissions into a hybrid index, then serves agentic RAG, deep research, custom agents and an MCP server.

ragagents
→ pairs well with Ollama, MaxKB
otari logo
2
mozilla-ai avatarmozilla-ai 953 · today
otari

Mozilla.ai's self-hosted AI gateway: one OpenAI/Anthropic-compatible endpoint over 40+ providers via any-llm, with virtual keys, pre-dispatch budgets, routing policies and a usage dashboard.

gateway
→ alternative to litellm, plano
nanoflow logo
4
nanosite-ai avatarnanosite-ai 15 · 16 days ago
nanoflow

Claude Code plugin that ties ticket → worktree → branch → ports → PR → CI → teardown together for parallel agent sessions, with a live dashboard pane, status line, toasts and a secrets vault.

codingorchestration
→ alternative to worktrunk, orca
taste-skill logo
3
Leonxlnx avatarLeonxlnx 118.8k · 11 days ago
taste-skill

Agent skill that art-directs coding agents into polished company websites — one design system, real photos and icons, restrained motion — verified in a real browser by a finish gate.

skills
→ pairs well with npxskillui, stop-slop
xerj logo
3
xerj-org avatarxerj-org 18.2k · today
xerj

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.

ragstorage
→ alternative to leviathan, omnigraph
WeKnora logo
6
Tencent avatarTencent 37.8k · today
WeKnora

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.

ragagents
→ pairs well with TencentDB-Agent-Memory, MaxKB
TencentDB-Agent-Memory logo
4
TencentCloud avatarTencentCloud 31k · today
TencentDB-Agent-Memory

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.

memorygateway
→ pairs well with WeKnora, hivemind
swe-sweep logo
0
facebookresearch avatarfacebookresearch 246 · 7 days ago
swe-sweep

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.

evalscoding
openqodex logo
3
openqodex avataropenqodex 1.2k · today
openqodex

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.

codingevals
→ pairs well with opencode, open-code-review
opencode logo
7
anomalyco avataranomalyco 228k · today
opencode

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.

codingagents
→ pairs well with CodeNomad, orca
leviathan logo
3
elstongun avatarelstongun 884 · 10 days ago
leviathan

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.

memorydata
→ alternative to xerj, context-mode
iFixAi logo
3
ifixai-ai avatarifixai-ai 46.5k · today
iFixAi

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.

evalssecurity
→ pairs well with garak, giskard-oss
helix-foundry logo
4
HelixDB avatarHelixDB 2.2k · yesterday
helix-foundry

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.

knowledge-graphsdata
→ alternative to context-ontology-accelerator, ontobricks
harness2 logo
3
google-research avatargoogle-research 24.5k · 17 days ago
harness2

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.

agentsevals
→ alternative to JIT, agentic-context-engine
graphicle logo
5
Graphicle-AI avatarGraphicle-AI 581 · 3 days ago
graphicle

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.

code-intelmemory
→ alternative to codebase-memory-mcp, gortex
cortexdb logo
5
liliang-cn avatarliliang-cn 528 · 2 days ago
cortexdb

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.

memoryknowledge-graphs
→ pairs well with deepseek-harness, engrim
anatomy logo
1
wheresryan22 avatarwheresryan22 28.2k · 1 months ago
anatomy

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.

skills
→ alternative to archify
agent-orchestration-standard logo
3
tomtomsatnav avatartomtomsatnav 104 · 2 days ago
agent-orchestration-standard

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.

orchestrationcoding
→ alternative to agent-flow, abtop
uzu logo
5
trymirai avatartrymirai 3.4k · today
uzu

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.

localdecision-models
→ alternative to coreai-models, xybrid
typesafe-computer-use logo
6
awlevin avatarawlevin 1.3k · 1 months ago
typesafe-computer-use

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.

agentsdecision-models
→ pairs well with pg-jev, Ollama
Strata logo
5
Niko1221 avatarNiko1221 45.9k · yesterday
Strata

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.

localcoding
→ pairs well with Lynkr, FreeToken
rea logo
3
morluto avatarmorluto 469.5k · today
rea

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.

securitycode-intel
→ pairs well with deepseek-harness, open-kritt
pg-jev logo
3
realZachi avatarrealZachi 1.3k · 1 months ago
pg-jev

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.

datadecision-models
→ pairs well with typesafe-computer-use, pgGraph
operator-memory logo
5
aerovato avataraerovato 519 · 14 days ago
operator-memory

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.

memorycoding
→ pairs well with deepseek-harness, Trellis
openrig logo
6
mvschwarz avatarmvschwarz 8.9k · today
openrig

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.

orchestrationcodingagents
→ pairs well with beads, squad
OpenDots logo
5
CopilotKit avatarCopilotKit 6.7k · yesterday
OpenDots

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.

agentsorchestration
→ alternative to openworker, qm
Octop logo
4
TencentCloud avatarTencentCloud 12.3k · today
Octop

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.

agentsorchestration
→ alternative to mateclaw, brigade
project-minigraf avatar
3
project-minigraf avatarproject-minigraf 229 · today
minigraf

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.

knowledge-graphsmemorystorage
→ alternative to latticedb, oxigraph
dosco avatar
4
dosco avatardosco 3.2k · today
graphjin

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.

data
→ pairs well with mcp-context-forge, ktx
e2e logo
3
e2e-inc avatare2e-inc 14k · today
e2e

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.

evalsweb
→ pairs well with browser, typesafe-computer-use
context-mode logo
6
mksglu avatarmksglu 34.3k · today
context-mode

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.

codinglocal
→ pairs well with codeburn, token-optimizer
uber avatar
3
uber avataruber 2.1k · 6 days ago
ADR

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).

securityevals
→ pairs well with Adrian, numbat
moli logo
2
lexmount avatarlexmount 24.1k · today
moli

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.

webagents
→ pairs well with browser-use, browser
edgextract logo
4
raphaelmansuy avatarraphaelmansuy 146 · 18 days ago
edgextract

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.

knowledge-graphsdecision-models
→ alternative to Hyper-Extract, ontocast

One email a week: what changed in the AI stack

New repos, new typed connections, the why behind each. No spam, unsubscribe anytime.