Local-first developer tools

• DuckDBIn-process OLAP database

  Free / OSS · OSS/MIT · 42.3k GitHub stars

  VerdictLocal analytics that just works.

  CatchNot for OLTP workloads—it is analytics-focused. Single-node limits apply. Less ecosystem than traditional databases.

• OpenAI Codex CLIApache-2.0 OpenAI agent: CLI, IDE, app and cloud

  Free / OSS · Freemium · 130k GitHub stars

  VerdictOpenAI’s answer to terminal agents — open CLI, paid models; budget the plan or the API.

  CatchThe CLI is open source, but the models are not free: you pay through ChatGPT plan quotas or API spend. Codex Web runs on OpenAI’s cloud, not on your machine. The install.sh, brew and npm routes are supply-chain choices, so pin a release binary when that matters. Vs Claude Code or OpenCode: this is OpenAI’s first-party agent, tied to ChatGPT plans or OpenAI API keys.

• GooseLocal-first Rust agent with MCP at its core

  Free / OSS · OSS/MIT

  VerdictLocal-first, MCP-native, model-agnostic. Bring your own brain.

  CatchGeneral-purpose agent means you configure it for your use case. You bring the model—Goose is the runtime, not the intelligence. Documentation is still maturing.

• Needle 214MB on-device tool-calling model

  Free / OSS · Apache-2.0 · 14.1k GitHub stars

  VerdictTiny on-device tool-caller. One job, done locally.

  CatchNot a chat LLM. Needle does one thing: parse user intent into tool calls. You still need the tools and the orchestration around it. Do not expect conversation or reasoning.

• BentoMIT slide decks as a single HTML file

  Free / OSS · OSS/MIT · 5.5k GitHub stars

  VerdictOne-file MIT slides. Useful, small, not a productivity suite.

  CatchReveal.js-based. This is slides-for-agents, not an office suite. Not BentoML and not bentonow.com.

• PromptfooMIT LLM evals & red-teaming CLI; Community free, 10k probes/mo

  Free / OSS · Freemium · 26.1k GitHub stars

  VerdictMIT eval/red-team CLI. Free core; probe cap + Enterprise sales wall.

  CatchVs DeepEval/Braintrust: YAML/CLI-first, not pytest-native Python or Braintrust SaaS. Community caps red-team probes (~10k/mo); Enterprise/On-Prem are contact-sales (SSO, dashboards, dedicated runner). LLM API costs are yours. Acquisition governance is a multi-year bet.

• DeepEvalApache-2.0 pytest-style LLM/agent evals; Confident AI is the paid cloud

  Free / OSS · Apache-2.0 · 18.9k GitHub stars

  VerdictApache-2.0 LLM unit tests. Free locally; Confident AI starts free then $200.

  CatchOSS is the runner — collaboration/dashboards/monitoring are Confident AI (Free: 2 seats/1 project/5 runs/wk; Starter $200/mo; Team $2k/mo). LLM-as-judge burns provider tokens. Vs Ragas: broader agent/chat coverage, not RAG-only.

• GrypeApache-2.0 SBOM-first vulnerability scanner from Anchore; free CLI

  Free / OSS · Apache-2.0 · 13k GitHub stars

  VerdictApache-2.0 SBOM vuln scanner. Free CLI; Enterprise is the paid cousin.

  CatchVuln scanner — not Trivy's IaC/secrets swiss-army, not Cosign signing, not Anchore Enterprise governance UI. You still triage CVEs. Anchore monetizes Enterprise separately.

• OllamaMIT local model runner — free forever; Pro cloud $20/mo

  Free / OSS · Freemium · 184k GitHub stars

  VerdictMIT local runner. Free on device; Pro is optional cloud.

  CatchModel runner, not a coding agent. Distinct from vLLM (server serving) and LM Studio (GUI desktop app). You still pick models, prompts, and the agent layer on top.

• ChromaApache-2.0 open-source embedding database for AI apps

  Free / OSS · Apache-2.0 · 29.5k GitHub stars

  VerdictApache-2.0 embedding DB. Free self-host.

  CatchHosted Chroma is commercial; self-host ops still yours. Distinct from Qdrant and Pinecone.

• OpenCodeMIT OSS coding agent: CLI, TUI, desktop; BYOK/local

  Free / OSS · OSS/MIT · 217k GitHub stars

  VerdictMIT BYOK agent across CLI/desktop/IDE. The real catches are on /log: date stamp and compaction.

  CatchTwo catches worth reading on /log: “The date stamp is a trigger channel” (auto today’s-date × open-weight LoRA as a time-release fuse) and “Compaction ate the denial” (long sessions prune hard vetoes; compaction is untrusted rewrite). Re-read those two notes before you treat OpenCode as set-and-forget.

• BrunoMIT git-native API client; Pro/Ultimate are optional seats

  Free / OSS · OSS/MIT · 47.7k GitHub stars

  VerdictMIT git-native API client. Free forever for local + CLI; pay only if the team wants the licensed desktop extras.

  CatchCore client is free forever; Pro (~$6/user/mo billed annually) and Ultimate (~$11) unlock in-app Git UI, OpenAPI sync quotas, and org admin. Golden Edition is sunset for new buys. Not a mock/monitor platform like Postman Cloud. Hoppscotch is the web-first alternative.

• SOPSMPL-2.0 encrypts config values; keys stay readable

  Free / OSS · MPL-2.0 · 23.4k GitHub stars

  VerdictMPL-2.0 secrets-in-git. Free forever; use age underneath when you want KMS-free recipients.

  CatchVs age (file encryption) and Infisical (secrets product): SOPS is the *structured config encryptor*, not a password manager and not a hosted vault UI. You still design key distribution, rotation, and who can decrypt in CI. Binary mode encrypts whole files when structure does not apply.

• SemgrepLGPL-2.1 SAST engine; Free Edition caps repos/contributors

  Free / OSS · LGPL-2.1 · 17.1k GitHub stars

  VerdictLGPL SAST. Free forever CLI; Free Edition SaaS for small teams; Teams when AppSec wants the paid platform.

  CatchVs Trivy/Gitleaks (scanners): Semgrep is SAST/SCA-shaped AppSec, not container CVE inventory or git-history secret regex alone. Teams starts ~$30/contributor/mo per product; Secrets is a separate SKU. Free Edition caps contributors/repos — OSS CLI without the SaaS seat is the uncapped escape hatch.

• k6AGPL-3.0 scriptable load testing (JS) from Grafana

  Free / OSS · AGPL-3.0 · 32k GitHub stars

  VerdictAGPL-3.0 scriptable load. Free unmodified CLI/CI; Cloud k6 is the paid seat.

  CatchAGPL-3.0 network/copyleft — modifications you serve or distribute can trigger source obligations; do not treat k6 as MIT. Grafana Cloud k6 is a separate paid hosted product (execution, analysis, collaboration). Vs oha (MIT TUI hammer): k6 is the *scripted/scenario* suite, not a live ratatui chart. Point it at staging you own.

• OSV-ScannerApache-2.0 OSV.dev vulnerability scanner for lockfiles and images

  Free / OSS · Apache-2.0 · 11.2k GitHub stars

  VerdictApache-2.0 OSV.dev scanner. Free forever; pair with Trivy/Grype/Syft, do not clone them.

  CatchVs Trivy/Grype (broader/image-first scanners) and Syft (*SBOM producer*): OSV-Scanner is the OSV.dev-native vuln CLI, not a replacement for every Trivy filesystem/misconfig check and not the SBOM generator. Complements those tools; do not expect identical CVE sets. Networked API unless you go `--offline`.

• TaskMIT Taskfile.yml runner — YAML alternative to Make/just

  Free / OSS · OSS/MIT · 16.3k GitHub stars

  VerdictMIT Taskfile runner. Free forever; just stays the justfile gem, Task owns Taskfile.yml.

  CatchVs just (CC0 *justfile* command runner): Task is *Taskfile.yml* with includes/deps as a first-class YAML graph — not a thin twin of just, and not Make’s implicit DAG. Still a command runner, not a build system or package manager. Pick one runner per repo or you will confuse newcomers.

• Open InterpreterApache-2.0 terminal coding agent; Rust Codex fork for open models

  Free / OSS · AGPL-3.0 · 68.6k GitHub stars

  VerdictApache-2.0 open-model terminal agent. Use the Rust line; classic Python is a fork.

  CatchVs Claude Code / Cursor / OpenCode / Gemini CLI: this is open-model/BYOK terminal, not a hosted Max seat. 2026 rewrite — Rust Codex fork; classic Python AGPL lives at endolith/open-interpreter community fork. The old pip interpreter UX is no longer current upstream.

• RowboatApache-2.0 local-first AI coworker — knowledge graph + MCP

  Free / OSS · Freemium · 18k GitHub stars

  VerdictApache-2.0 local AI coworker. Graph memory + MCP; paid cloud is optional.

  CatchVs OpenClaw / Continue / Claude Code (coding seats) and Mem0/Letta (memory runtimes): Rowboat is a full coworker desktop with graph memory, not a library you embed. Hosted Starter/Pro plans are paid convenience; OSS/local path is the free forever bar. Shell access on your machine means trust boundaries matter.

• GriptapeApache-2.0 Python agents, pipelines, RAG — MCP tools too

  Free / OSS · Apache-2.0 · 2.6k GitHub stars

  VerdictApache-2.0 Python agent/RAG framework. MCP as tools; Cloud free tier is metered, not forever.

  CatchVs LangChain/LangGraph and CrewAI: Griptape is a structured Python agent/RAG framework, not a coding CLI. Cloud Developer free tier needs a payment method on file and meters after small included quotas — pitch the OSS framework first, not Cloud as free forever.

• agentsviewMIT local-first agent session/cost archive — 20+ coding agents

  Free / OSS · OSS/MIT · 6.2k GitHub stars

  VerdictMIT local agent archive. Session/cost on disk; not Langfuse/Braintrust cloud.

  CatchVs Langfuse / Braintrust (cloud LLM observability): agentsview is a local session/cost archive for coding-agent transcripts, not a hosted tracing/eval platform. Optional anonymous telemetry ping; you still need the agent logs on disk. Not a replacement for production OpenTelemetry of your app’s LLM calls.

• EngramMIT persistent agent memory — MCP, CLI, TUI, SQLite

  Free / OSS · OSS/MIT · 7.4k GitHub stars

  VerdictMIT agent memory primitive. MCP/CLI/TUI on SQLite; not a full agent framework.

  CatchVs Mem0 / Letta / full agent frameworks: Engram is the memory primitive (store + retrieve + surfaces), not an orchestration framework or coding agent. “local or cloud” branding means optional hosted/sync gravity — day-one stays OSS you run. You still decide what gets written and when.

• HarperApache-2.0 offline privacy grammar checker — Rust (Automattic)

  Free / OSS · Apache-2.0 · 16.7k GitHub stars

  VerdictApache-2.0 offline grammar. Privacy-local vs Grammarly cloud.

  CatchVs Grammarly SaaS: Harper is offline Rust grammar, not a cloud writing coach with tone/generative rewrites and team admin. Rule coverage and language support differ from Grammarly’s product surface — try it on your real prose. Not an LLM writing agent.

• OpenResearchMIT coding agents → research agents (Rust)

  Free / OSS · OSS/MIT · 7.3k GitHub stars

  VerdictMIT research-agent workspace. Coding agents → autoresearch; not Spec Kit/DSPy/Promptfoo.

  CatchVs Spec Kit (spec-driven coding workflow), DSPy (prompt/program optimizers), Promptfoo (eval/red-team): OpenResearch is a research-agent harness and experiment ledger around existing coding agents — not a spec kit, not a prompt compiler, not an eval suite. You still pay (or self-host) the coding agent and any remote compute you dispatch.

• Atlas (pacifio)MIT multi-agent change tracking — source control for agents

  Free / OSS · Apache-2.0 · 9.6k GitHub stars

  VerdictMIT agent source-control. pacifio Atlas ≠ Ariga Atlas; track agents, not schemas.

  CatchVs Worktrunk/jj (git worktree / change-oriented VCS plumbing): Atlas is agent session+change tracking with shared memory, not a general VCS replacement. name collision with Ariga Atlas (slug `atlas`, schema-as-code) — this card is `atlas-agents` / pacifio only; never confuse with atlasgo.io.

• VoiceboxLocal-first OSS voice studio — clone, TTS, dictate, MCP voice for agents

  Free / OSS · OSS/MIT · 58k GitHub stars

  VerdictMIT local voice studio. Install when agents and humans need on-device TTS/STT without a cloud voice vendor.

  CatchLocal GPU/CPU and model downloads are on you; macOS/Windows desktop footprint is heavier than a REST TTS call. Large open-issue count — treat cutting-edge engines as experimental. Vs ElevenLabs-class cloud TTS (paid APIs) and Whisper-only STT stacks: Voicebox owns both ends of the loop locally, with agent voice as a first-class surface.

• Pizza BotLocal-first inbox for long-running AI agent work

  Free / OSS · Apache-2.0 · 502 GitHub stars

  VerdictApache-2.0 agent inbox. Use when long-running agent jobs need Unread/Action queues instead of a single chat thread.

  CatchVs OpenBot / nanobot (coworker computers or personal gateways) and Thurbox (tmux multi-agent panes): Pizza Bot is the async work inbox, not a governed desktop coworker or a pane orchestrator. The api-server process must stay up; you bring model keys and operate the stack. Early OSS surface — pin versions.

• TradingView MCPLocal CDP bridge: Claude/agents on your TradingView Desktop charts

  Free / OSS · OSS/MIT · 6.9k GitHub stars

  VerdictOpen MCP for agents on your TradingView Desktop. Paid TV sub required; chart interface layer, not a trading bot.

  CatchYou need a valid paid TradingView subscription plus Desktop with remote debugging enabled — the bridge does not bypass paywalls. Undocumented Electron internals can break on any TradingView update. Vs playwright-mcp / BrowserSkill / Hyperbrowser MCP: this is desktop TradingView CDP, not a general browser or scrape API. Not a trade-execution bot.

• gawkbotSource-available always-on bots that build microapps — local Grok Bot alternative

  Free / OSS · Open-Core · 1.5k GitHub stars

  VerdictSource-available local Grok Bot. Approval-gated personal bots; check SUL before you ship it as a product.

  CatchSustainable Use License — source-available, not OSI open-source; read the license before commercial redistribution. Vs OneCLI / AgentBox / Dexto: gawkbot is personal always-on bots + microapps, not a team credential gateway or Elastic-licensed harness. You still bring a signed-in coding agent CLI and model spend. Per-bot VM computers are still on the roadmap per README.

• Jev ReviewLocal MCP that scores coding-agent diffs with TypeSafe Jev

  Free / OSS · Freemium · 243 GitHub stars

  VerdictMIT MCP wrapper over paid Jev. Use for continuous in-agent quality signals when you already have a TypeSafe key.

  CatchScoring depends on a paid/early-access TypeSafe Jev API key — the MCP is OSS, the brain is not (same family as typesafe-computer-use). Vs CodeRabbit/PR bots: this is an in-loop agent checkpoint, not a GitHub review bot. Jev returns scores, not prose root-cause essays — the coding agent still has to diagnose.

More with this tag (36)

• OpenHuman — GPL-3 local-first agent orchestrator with memory trees and MCP
• Agentao — MIT governed Python agent runtime — permissions, MCP, memory, replay
• git-bug — GPL-3.0+ offline-first bugs stored inside the git repo
• StarNet — MIT local-first pixel-art desktop station for real agent crews
• FrontMCP — Apache-2.0 TypeScript-first MCP server framework (decorators, DI, OAuth)
• Cumora — MIT team chat where AI agents are first-class teammates
• WebCodex — Apache-2.0 bridge cloud AI agents to your local machine
• SkillOpt — MIT skills optimizer — trains skill.md as params for frozen agents
• Magnitude — Apache-2.0 local inference desktop+CLI — consumer profiler for agents
• Cognee — Apache-2.0 AI memory platform — local knowledge graph for agents
• Zeron — MIT local control plane for coding agents — optional multi-device sync
• MCP Scanner (Cisco) — Apache MCP security scanner — YARA, LLM, Cisco AI Defense
• HOL Guard — Apache local antivirus for agents — MCP, skills, shell, packages
• Apify MCP Server — MIT Apify Store MCP — agents scrape via thousands of Actors
• OpenDesign — Apache collaborative design-agent workspace — Claude Design alt
• OpenKnowledge — GPL-3.0 local markdown IDE + LLM wiki — MCP/skills for agent editing
• PageIndex — MIT self-hosted vectorless tree-RAG core — local mode with your own LLM key
• Plannotator — MIT/Apache local browser review for agent plans, docs and diffs — feedback goes straight back to the agent
• Omnigent — Apache-2.0 meta-harness over Claude Code, Codex, Cursor, Pi and custom agents — sessions on any device, policies, sandboxes
• Kubescape — Apache-2.0 CNCF Kubernetes security — manifest and cluster scans, image CVEs, auto-fix, admission policies, MCP server
• REA — MIT MCP server for agent-driven reverse engineering — binaries, Electron apps, .NET, websites
• Dyad — Local, open-source AI app builder — a v0/Lovable/Bolt alternative on your own machine
• Handy — MIT offline push-to-talk dictation for any text field — Whisper or Parakeet, nothing leaves your machine
• PPT Master — MIT agent skill that turns documents into natively editable PowerPoint decks — real shapes, charts and slide masters
• Codync — Apache-2.0 bots for Claude Code, Codex, Cursor and 40+ ACP agents — message them from phone or desktop
• MongoDB MCP Server — Apache-2.0 official MCP server for MongoDB
• preloop — MIT self-hosted GitHub Actions with microVM-isolated jobs
• uzu — MIT on-device inference engine for Apple Silicon apps
• EdgeQuake — Apache-2.0 GraphRAG engine in Rust, runs on local models
• Apache Maka — Apache-2.0 local-first agent workspace that logs every step
• PGlite — Apache-2.0 Postgres compiled to WASM for browser, Node, Bun and Deno
• RxDB — Apache-2.0 local-first reactive database for JavaScript apps
• Grist — Apache-2.0 relational spreadsheet you can self-host
• Laminar — Apache-2.0 tracing, evals and signals for AI agents
• ripwire — Apache-2.0 offline code map and quality checks for coding agents (CLI + MCP)
• Ragas — Apache-2.0 RAG/agent eval metrics — synthetic data + CI scorers