Cilium is a Kubernetes-native networking, observability, and security solution built on eBPF. It provides CNI plugin functionality with overlay/native routing modes, distributed load balancing (replacing kube-proxy), cluster mesh for multi-cluster connectivity, identity-based network policies (L3-L7), service mesh with mutual authentication, and observability via Hubble (flow metrics, DNS insights). The architecture features a modular design using the Hive dependency injection framework, with components including the cilium-agent daemon, operator for CRD management, CLI tools for management/debugging, and API servers for inter-component communication. The data plane leverages eBPF/XDP for high-performance packet processing, while the control plane integrates deeply with Kubernetes through client-go, controller-runtime, and custom resource definitions.
Capstone is a multi-architecture disassembly engine written in C, derived from LLVM's MC disassembler. It supports over 20 architectures including x86, ARM, AArch64, MIPS, PowerPC, RISC-V, and more. The core library provides a stable C API (cs_open, cs_disasm, cs_option, etc.) and includes per-architecture backends with mapping, disassembler, and instruction printer modules. The architecture is modular: each architecture has a Module.c that registers callbacks into a common cs_struct. The primary data flow is: user provides raw bytes and arch/mode, the engine selects the appropriate disassembler, decodes instructions into MCInst, then prints via instruction printer, optionally filling cs_detail with operand/register/group information. The repository also includes a CLI tool (cstool), extensive test suites (MC regression tests, cstest YAML-based detail tests), fuzzing harnesses, and an automated LLVM sync pipeline (auto-sync) that translates LLVM C++ disassembler code to C using tree-sitter patches. The codebase is well-structured with clean abstractions for operand models (MCInst/MCOperand), string output (SStream), and architecture-specific mapping. The auto-sync tooling is a notable engineering achievement, enabling systematic translation of LLVM backend code to C. Language bindings for Python, Java, OCaml, and others demonstrate the library's embeddability. The test infrastructure is comprehensive, covering both basic disassembly and detailed operand/register analysis. External dependencies are minimal for the core library (pure C), but the auto-sync tooling depends on Python, tree-sitter, clang-format, and lit. Overall, Capstone is a mature, actively maintained disassembly framework with high craftsmanship and reusable components.
Aya is a Rust framework for developing, loading, and managing eBPF (extended Berkeley Packet Filter) programs. It provides a pure-Rust alternative to libbpf and bcc, allowing developers to write eBPF programs in Rust without leaving the language ecosystem. The framework supports various eBPF program types (XDP, socket filters, tracepoints, kprobes, uprobes, LSM, etc.) and map types (arrays, hash maps, perf event arrays, ring buffers, etc.), with strong emphasis on type safety and developer experience. Aya implements BTF (BPF Type Format) support for compile-once-run-everywhere portability across kernel versions and provides procedural macros to reduce boilerplate when defining eBPF entities. The architecture consists of multiple crates separating userspace and kernel-space concerns, with extensive integration tests validating functionality against actual kernels.
libbpf-rs is a Rust workspace providing safe, idiomatic bindings to the Linux libbpf C library for eBPF program development. It consists of two main crates: `libbpf-rs`, a high-level runtime library for loading, attaching, and managing eBPF programs and maps, and `libbpf-cargo`, a Cargo plugin that compiles eBPF C source files and generates Rust skeleton code with type-safe accessors and lifecycle management. The library supports a wide range of eBPF attachment types (kprobes, tracepoints, XDP, TC, netfilter, etc.), CO-RE (Compile-Once-Run-Everywhere) via BTF, and includes utilities like ring buffer and perf buffer helpers, a query interface for inspecting loaded kernel objects, and a linker for combining multiple BPF objects. Architecture is a workspace with library crates and numerous example applications (e.g., runqslower, tcp_ca, tproxy) demonstrating real-world usage. Entry points include `ObjectBuilder`, `SkeletonBuilder` (from libbpf-cargo), and generated skeleton APIs. The project relies on `libbpf-sys` for FFI, and examples use `clap` for CLI and `plain` for safe byte conversion. It is heavily tested with integration tests requiring root privileges.
picosnitch is a Linux daemon for per-executable network bandwidth monitoring using eBPF (CO-RE) and fanotify. It tracks which executables make network connections, records bytes sent/received, timestamps, and metadata (SHA256 hashes, optional VirusTotal and GeoIP lookups). The system provides real-time and historical views via multiple interfaces: a curses TUI (both live top and historical browser), a web UI, and a UNIX socket live feed. The daemon uses a multiprocess architecture with privilege-separated subprocesses for monitoring, event processing, database writes, notifications, and external API queries. It supports local SQLite storage and optional remote SQL (MariaDB/MySQL/PostgreSQL) for tamper-evident logging. The repository also includes a comprehensive comparative benchmark suite (bench/) that tests picosnitch against nine other network monitors across 24 scenarios, with a reusable ToolAdapter framework for running controlled experiments.
Tracee is a runtime security and observability tool that uses eBPF to trace system events and detect threats. It consists of multiple Go binaries: a main security agent (`tracee`) that loads eBPF programs, collects kernel events, and runs detection rules; a gRPC client (`traceectl`) for remote management; an event generator (`evt`) for stress testing; and a Kubernetes operator. The architecture is modular with a clear separation between eBPF event collection, event derivation and enrichment pipelines, data stores (process tree, container info, DNS cache, kernel symbols), a detection engine supporting both Go signatures and YAML-based rules using CEL expressions, and filtering/policy subsystems. The system operates as a daemon with HTTP/gRPC endpoints for metrics, health, and streaming event output, and integrates deeply with Kubernetes via CRDs and controllers. The codebase demonstrates strong engineering with clean abstractions (filter interfaces, data store registries, event derivation framework), reusable utility packages (bucketcache, changelog, string interning, fuzzy parsing), and comprehensive testing including unit, integration, and e2e tests. However, it exhibits technical drift in areas like multiple Go modules with `replace` directives, hardcoded kernel version checks in eBPF probe logic, legacy signature conversion code planned for removal, and some global mutable state. The eBPF C code is complex and kernel-version-sensitive, requiring ongoing maintenance. Overall, it is a well-crafted, production-grade security tool suitable for container and Kubernetes environments.
Parca is a continuous profiling platform that collects, stores, queries, and visualizes pprof profiles in real time. The Go backend ingests profiles via gRPC (both pprof and OpenTelemetry OTLP), normalizes them into Apache Arrow columnar format, and stores them in either FrostDB (default) or ClickHouse. It provides a rich gRPC+JSON API for querying profiles (flamegraph, table, source view, callgraph, pprof download), scraping Prometheus-style targets, managing debug information for symbolization, and sharing profiles via links. The TypeScript/React frontend delivers an interactive profiling UI with flamegraphs, tables, source views, metrics graphs, sandwich views, and comparison mode, all backed by efficient Arrow-based querying. The codebase demonstrates strong engineering with reusable patterns (generic caching, signed request abstraction, Arrow compaction), but carries some drift risk from dual storage backends, generated protobuf code, and a complex UI state layer built with multiple state management strategies.
KernelScript is a domain-specific language and compiler (OCaml) for developing eBPF-centric programs. The compiler translates a single `.ks` source file into multiple C outputs: idiomatic eBPF C code (for kernel execution via XDP, TC, kprobe, tracepoint, perf_event, struct_ops), userspace loader C code (managing maps, ring buffers, tail calls, and program lifetime), and optionally kernel module C code (for `@kfunc` functions). The compiler pipeline includes lexing, parsing, symbol table construction, type checking (including context-specific rules for eBPF program types), IR generation with control-flow and data-flow analysis, loop analysis (bound detection, bpf_loop optimization), tail-call detection and automatic progarry management, map assignment optimization, safety checking (null pointer, bounds, overflow), and multi-program optimization (map type changes, batching). It also supports BTF introspection for kernel type and kfunc extraction, a Python bridge, and a compile-time evaluator. The architecture is modular with pluggable context code generators per program type. The project includes an extensive test suite covering the full pipeline from parse to C output and specific features like perf_event attach, ring buffer dispatch, struct_ops, and multi-program scenario.
Honey Potion is a compiler framework that translates a subset of the Elixir programming language into eBPF (extended Berkeley Packet Filter) programs, targeting both tracepoints and XDP. The system works as an Elixir library (published on Hex as `honey`) where users write eBPF logic in Elixir using macros like `@sec`, `defmap`, and `fuel`. At compile time, `__before_compile__` triggers a pipeline: static analysis, optimization (constant propagation, dead code elimination, type propagation), AST-to-C translation, boilerplate generation, and C compilation via `make`/`clang`/`llc`/`bpftool`. The generated C code includes a custom runtime with heap, tuple pool, and string pool implemented using BPF maps to overcome eBPF's stack and memory constraints. The repository includes 20+ example programs (system monitors, packet filters, data structure demos) and a comprehensive benchmark suite comparing hand-written C eBPF programs to Honey-generated ones, supporting a published research paper. Although classified as an application (a compiler library), the project has strong research characteristics with reproducible artifact scripts, optimizer variants, and performance comparisons.