model-agnostic repositories
Trending repositories tagged model-agnostic, ranked by trending score. Updated daily.
-
1
Axia-Growth/OperationKit
AI transformation infrastructure. A self-hosted knowledge base, agent board and MCP connection for putting AI to work inside a business. Run it in-house, license it as a consultant, or have us set up your server and run it for you. Works with Claude, Codex, Grok or open-weight models. Apache-2.0.
GitHub · TypeScript · 72 stars · 17 forks · +14 stars in 24 hours · Trending score 2.55
-
2
jdpolasky/chief-of-staff-2
An AI chief of staff in plain markdown, in an Obsidian vault. It tracks your calendar, commitments, and rules, and hands you a morning brief. Version two: torn down and rebuilt smaller. Built on Claude Code, ADHD-first, open to anyone.
GitHub · 70 stars · 3 forks · +27 stars in 24 hours · Trending score 2.41
-
3
aipoch/open-science
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
GitHub · TypeScript · 5,556 stars · 561 forks · +9 stars in 24 hours · Trending score 2.10
-
4
OpenCoven/coven
Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.
GitHub · Rust · 76 stars · 26 forks · 0 stars in 24 hours · Trending score 0.24
-
5
woai3c/x-code-cli
Open-source, model-agnostic coding agent CLI with subagents, skills, MCP, and plugins.
GitHub · TypeScript · 50 stars · 14 forks · 0 stars in 24 hours · Trending score 0.23
-
6
Balanov/shim
Tiny local-first AI harness: any model, MCP and Agent Skills, natural-language CLI. Zero dependencies. MIT.
GitHub · Go · 88 stars · 15 forks · −6 stars in 24 hours · Trending score 0.21
-
7
AmrDab/clawdcursor
Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR) and acts by element name, with screenshots as the last resort. Multi-monitor aware, verifies every action, one safety gate.
GitHub · TypeScript · 406 stars · 59 forks · 0 stars in 24 hours · Trending score 0.10
-
8
alessioricco/Certo
A coding-agent harness that isn't tied to one model or provider: it picks a model per task, switches when one fails, and checks the work with your own tests.
GitHub · Python · 8 stars · 6 forks · 0 stars in 24 hours · Trending score 0.09
-
9
KyaniteLabs/checkyourself
Local-first completion-evidence system for AI-built apps: read-only audit, verifier-executed challenges, evidence-based 0-100 score, guided fixes, learning plan, CLI, and MCP.
GitHub · Python · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
10
parvezrob/llmdispatch
Control which LLM handles each task in your app. Swap providers at runtime, fall back on failure, enforce per-user quotas. Framework-agnostic, no proxy.
GitHub · TypeScript · 10 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07
-
11
AbyssCN/oh-my-dag
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
GitHub · TypeScript · 44 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
12
avasol/galadriel-public
The open engine behind Aedelgard: a persistent, self-hosted AI agent with a verbatim memory palace and a model-agnostic brain. Swap Claude, Gemini, OpenAI, Mistral, DeepSeek or a local model without losing the mind.
GitHub · Python · 51 stars · 10 forks · 0 stars in 24 hours · Trending score 0.00
-
13
lunarstack-co/agentling
The agent loop for Python. Your harness, any model.
GitHub · Python · 26 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00
-
14
FlorianBruniaux/flow-lean
Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude Code and Codex.
GitHub · Python · 23 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
15
maziyarpanahi/ai-demos
Open-source AI demos you can understand, run, and remix — small, reproducible builds for vision, multimodal models, local or hosted inference, and more.
GitHub · Python · 13 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
16
ychampion/melete
Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model. Personal Superintelligence.
GitHub · TypeScript · 19 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
17
diggerhq/opendots
An always-on personal agent you own, on the model you choose. A model-agnostic alternative to OpenAI's Dots, built on OpenComputer Serverless Agents.
GitHub · TypeScript · 26 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00