Autonomous AI agents that perform tasks independently
brainsparker
CLI-first, open-source agent framework
svanhoofsensolus
Sensolus agent-app kit: Snt* widgets (merged from @sensolus/snt-ui), theme, colors, i18n framework. Locked shared code — import it, don't copy it.
...moreNorthwestern-CSSI
A dependency-free Python SDK that drives the APTO Code CLI over stream-json stdio, mirroring the Claude Agent SDK interface.
...moreQHarbor team
QUAlibrate connector for eTiKeT sync agent
Raghav Mishra (PowerAI Labs)
All seven Cendor libraries in one install — plain building blocks for LLM apps: context, cost, compression, a deterministic guardrails gate, testing, and a tamper-evident audit trail.
...moreRaghav Mishra (PowerAI Labs)
A local-first gate for LLM apps: define a check — keyword, regex, URL, length, JSON-schema — attach it to a stage (input, tool call, tool output, output). Deterministic, microsecond, $0, and every decision is audit-grade evidence.
...moreMulti-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations; fast local tiers screen every request, only uncertain cases reach an LLM judge
...morefractaal
Agentic process lifecycle tools for Pi: background bash tasks, sparse monitors, and headless management APIs.
LangChain tools for querying Uniswap V2 pools: swap quotes, liquidity previews, and LP balances across any EVM chain.
study8677
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
...morelinmy666
MadCop — local-first AI agent desktop workstation (v0.9). Multi-model chat (GLM-5.2/DeepSeek/Qwen3), tool-use, MCP servers, 12 workflow modes, knowledge base, AI design tool, persistent workspace integration. AGPL-3.0.
...moreAzure-Samples
A hands-on, step-by-step workshop for building a Travel Assistant agent on Microsoft Foundry hosted agents with the Agent Framework - growing from a single agent to a multi-agent planner with function tools, MCP, RAG, workflows, and memory. Keyless auth throughout.
...moredevmrbouh-hub
Architecture for autonomous agent organizations: minimally sufficient teams per mission. Director, parametric sizing, Workspace-centric memory.
...morekdeps
Run AI workflows locally. Or deploy them anywhere. AI agent framework in YAML — workflow pipelines + autonomous agent loop. NVIDIA Inception member. Build, deploy, export as Docker/K8s/ISO.
...moreMikhailXiaomaikou
AI research workbench for observational cosmology that provably refuses to fabricate — every number traces to a registered dataset, or it abstains.
...moremetric-space-ai
Standard grep, plus a few commands your coding agent can use to navigate code — who-calls, impact, semantic-search, brief... up to ~2x faster and ~3-4x cheaper agentic code navigation. One native Rust binary.
...moreHardZionL
Domain-specific Agent for Linux kernel CVE livepatch generation, guarded tool execution, kpatch build validation, and evidence-based task state reconciliation.
...moreiammonth1997
AI Research Wiki 2026: Auto-Building Knowledge Base with Deep Citation Syntheses
Varun Gupta
A dashcam for your AI agents: local, tamper-evident recorder for process/file/network activity, with a LangChain/LangGraph drop-in prompt-injection circuit breaker.
...moreVarun Gupta
A dashcam for your AI agents: local, tamper-evident recorder for process/file/network activity, with a LangChain/LangGraph drop-in prompt-injection circuit breaker.
...moreluxay08
Thin runtime wrapper around the Swytchcode CLI
AgentProof
CLI security scanner: probes AI-agent HTTP endpoints for secret/prompt leakage, with CI-gating exit codes.
mingrath
Configure AI agents through markdown, not code. SOUL/MEMORY/skills pattern for building multi-agent AI systems.
Akash Shukla
Semantic skill registry for LLM agents — register, retrieve, and evaluate Cursor-style skills