sipyourdrink-ltd/bernsteinThe open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Python★ 1,1782026年9月14日
preloop/preloopThe open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails
Python · TypeScript★ 62↓ 364/月2026年9月18日
yvgude/lean-ctxLeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
Rust★ 3,893↓ 917/月2026年10月20日
Cranot/roam-codeLocal codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.
Python★ 516↓ 5,430/月2026年9月8日
cordum-io/cordumThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
Go · TypeScript · Python★ 505↓ 14/月2026年9月17日
jordigilh/kubernautAn AIOps platform that closes the loop from Kubernetes alert to automated remediation: An AI Agent investigates via MCP tools, selects a fix from a pre-seeded workflow catalog and delegates execution (K8s Job, Tekton, Ansible) — or escalates with a full RCA. Approval gates, OPA policies, and audit trails keep humans in control.
Go★ 352026年10月20日
Go · TypeScript · Python★ 67↓ 3,281/月2026年10月9日
vaaraio/vaaraAccountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.
Python★ 15↓ 7,475/月2026年10月20日
basilisk-labs/agentplane🛩️ Git-native workflow control for coding agents: approved plans, verification, and reviewable evidence for Claude Code, Codex, Cursor, and Aider.
TypeScript · JavaScript★ 76↓ 9,641/月2026年9月6日
g8e-ai/g8eA zero-trust execution platform that safely bridges AI agents and infrastructure without surrendering data sovereignty
Go · Python★ 72026年9月10日
peg/rampartOpen-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.
Go★ 832026年9月6日
TypeScript★ 7↓ 86/月2026年9月20日
PHP★ 126↓ 4,808/月2026年10月21日
lua-ai-global/governanceZero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
TypeScript★ 26↓ 18.7K/月2026年9月13日
mnemox-ai/tradememory-protocolDecision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
Python★ 1,425↓ 569/月2026年9月30日
thyn-ai/algenta-sdkPython and TypeScript SDKs for Algenta — self-hosted building blocks for AI applications. 6,000+ deterministic functions on custom Mojo kernels behind one API, SDK and MCP surface; no new language to learn. The engine is proprietary; the SDKs, API contract and examples are Apache-2.0. Siblings: thyn-ai/algenta-integrations, thyn-ai/mojo-kernels.
TypeScript · Python★ 0↓ 6,521/月2026年9月24日
alizahidraja/isnadGrade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines
Python★ 53↓ 2,089/月2026年10月21日
TypeScript★ 28↓ 652/月2026年9月8日
npm · crates.io · Go80优秀健康指数
Rust★ 13↓ 10.2K/月2026年10月1日
PHP★ 122↓ 6,739/月2026年9月9日
teaql/teaql-javaAI-native Java library and runtime for business apps: model-driven, typed SQL queries, safe expressions and audited graph mutations.
Java★ 72026年10月19日
AlizHarb/filament-activity-logA powerful, feature-rich activity logging solution for FilamentPHP v4/v5 with timeline views, dashboard widgets, and revert actions.
PHP★ 31↓ 24.8K/月2026年9月11日
Keesan12/martin-loopMake AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.
TypeScript · JavaScript★ 51↓ 2,344/月2026年9月11日
padosoft/laravel-flowLaravel workflow engine: dry-run, compensation, approval gate, business impact tracker
PHP★ 4↓ 18.9K/月2026年10月20日
tuliplabs-ai/tulip-agentsThe agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.
Python★ 1↓ 5,295/月2026年10月8日
Drakon-Systems-Ltd/ShieldCortexMemory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.
TypeScript★ 25↓ 8,879/月2026年10月20日
Smeldr/coreTyped backend for decisions, tasks, and content: enforced lifecycle, role-gated ratification, and a relation graph that flags its own stale connections. MCP-native. Zero runtime dependencies. Self-hosted.
Go★ 72026年9月10日
PHP · Twig★ 475↓ 110K/月2026年9月11日
PHP★ 9↓ 14.4K/月2026年9月14日
getveritio/veritioProtocol-first OSS evidence layer for application audit trails, consent history, DSAR workflows, retention, and compliance exports.
TypeScript · Go · Python★ 0↓ 265/月2026年9月19日