mhtirogla
Home
Systems
API
Pricing
About
Log in
← Back
Home
›
Systems
›
AI and ML infrastructure
llm-gateway
LLM gateway and model router
LiteLLM, OpenRouter
System
Techniques · 23
Primitives · 92
llm-gateway
Model routing and cascades
agentic-ai · medium: Send each request to the cheapest model that will answer it well enough, by rules, a learned router, or a cascade that escalates from small to large on low confidence.
›
Semantic cache
agentic-ai · medium: Caching LLM responses keyed by embedding similarity of prompts, with thresholds and invalidation
Deterministic simulation testing
distributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.
›
Primary-backup replication
distributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.
›
Usage metering
finance · medium: Counting tokens/requests per user and key, aggregating for quotas and billing with idempotent events
Reverse proxy
networking · medium: A server-side intermediary that terminates client connections and forwards each request to one of a pool of upstream servers, with routing, health checks, timeouts and safe retries.
›
Coverage-guided fuzzing
security · medium: Mutate inputs, run an instrumented target, and keep any input that reaches a new code edge; feedback turns blind guessing into incremental search.
›
Circuit breaker
systems · low: Stop calling a failing dependency for a while, probe it with trial calls, and resume on recovery: fail fast instead of piling up timeouts.
›
Exponential backoff with jitter
systems · low: Retry after delays that grow geometrically and are randomized, so failed clients spread out instead of hammering a recovering service in synchronized waves.
›
Byte-pair encoding (BPE) tokenizati…
machine-learning · low: Learn a subword vocabulary by repeatedly merging the most frequent adjacent pair; byte-level BPE encodes any input losslessly with 32k-200k tokens.
›
Secrets management
security · low: Keep keys and passwords out of code and logs, give workloads short-lived identity instead of static keys, and make rotation routine.
›
Prompt caching
agentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.
›
Tool calling
agentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.
›
Hdr histogram
data-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentiles
Consistent hashing
distributed · low: Hash nodes and keys onto a ring; each key belongs to the next node clockwise, so membership changes move only about 1/n of keys.
›
Process supervision
hardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.
›
Power of two choices
networking · low: Pick two random backends and send to the less loaded one; exponentially better balance than random, with no global state and no herding.
›
Server-sent events
networking · low: One long-lived HTTP response carries text events one way; each event may carry an id, so a reconnecting client names its last one and the server resumes.
›
Mutual TLS
security · low: TLS where the client also proves a certificate key, so every connection carries a verified, rotatable machine identity.
›
GCRA
systems · low: Generic Cell Rate Algorithm: a token bucket stored as one theoretical arrival time per key, updated with one compare-and-swap; exact limits in 8 bytes.
›
Graceful draining
systems · low: On a termination signal, stop taking new work, finish in-flight work until a deadline, tell clients to reconnect elsewhere, then exit; clients resume from a token.
›
Hedged requests
systems · low: Sending a backup request after a latency percentile and taking the first answer to cut tail latency
Token bucket
systems · low: A bucket of up to b tokens refilled at rate r; requests spend tokens, enforcing an average rate while allowing bursts of b.
›
+ 16 more techniques
+ 76 more primitives
System
Techniques · 23
Primitives · 92
llm-gateway
Model routing and cascades
agentic-ai · medium: Send each request to the cheapest model that will answer it well enough, by rules, a learned router, or a cascade that escalates from small to large on low confidence.
›
Semantic cache
agentic-ai · medium: Caching LLM responses keyed by embedding similarity of prompts, with thresholds and invalidation
Deterministic simulation testing
distributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.
›
Primary-backup replication
distributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.
›
Usage metering
finance · medium: Counting tokens/requests per user and key, aggregating for quotas and billing with idempotent events
Reverse proxy
networking · medium: A server-side intermediary that terminates client connections and forwards each request to one of a pool of upstream servers, with routing, health checks, timeouts and safe retries.
›
Coverage-guided fuzzing
security · medium: Mutate inputs, run an instrumented target, and keep any input that reaches a new code edge; feedback turns blind guessing into incremental search.
›
Point-in-time recovery
storage · medium: Periodic base backups plus a continuously archived change log let you rebuild the state as of any instant, then branch from there.
›
Delta debugging
compilers · medium: Ddmin minimization of failing inputs or change sets
Fault injection
distributed · medium: Inject latency, errors, kills and partitions via proxies, netem or hooks
Multi-armed bandits
machine-learning · medium: Choose among K options repeatedly while learning their payoffs: epsilon-greedy, UCB1 and Thompson sampling keep total regret low where a fixed split or a fixed exploration rate pays forever.
›
Text classification
machine-learning · medium: Assign one or more labels to a text; climb a ladder from regexes to linear models on n-grams, embeddings, fine-tuned encoders and LLM prompts, only as far as the data and budget demand.
›
HNSW
search-sort · medium: Hierarchical Navigable Small World: a layered proximity graph searched greedily from a sparse top layer; the default in-memory approximate nearest-neighbour index.
›
Tls termination
security · medium: Terminate TLS at a proxy: SNI cert selection, session resumption, OCSP, kTLS offload (listed in Moved to the wiki)
ARIES recovery
storage · medium: Three-pass crash recovery (analysis, redo, undo) for steal/no-force buffer pools; repeats history, then rolls back losers with compensation log records.
›
Rollup aggregation
storage · medium: Fold raw events into one mergeable partial aggregate per time bucket and dimension key, then merge fine buckets into coarser ones, so long ranges read few rows and stay exact.
›
Cache invalidation
systems · medium: Make writes remove cached copies by key, group tag or prefix, broadcast the removal to every node, and guard refills with tokens so stale values never return.
›
Acme protocol
security · medium: Automated TLS certificate issuance and renewal via ACME HTTP-01/DNS-01 challenges
Key rotation
security · medium: Rotating keys without downtime: key ids, overlap windows, re-wrapping, JWKS publication, revocation
Syscall interception
security · medium: Intercept syscalls via ptrace, seccomp user notify or a user-space kernel
TLS 1.3
security · medium: The standard encrypted, authenticated transport; one round trip, only forward-secret AEAD suites, and little left to misconfigure.
›
Buffer pool
storage · medium: The database's own page cache (frames, page table, pin counts, dirty bits, replacement) so it, not the OS, controls eviction, write order and I/O.
›
Envelope encryption
security · medium: Encrypt each object with its own data key and wrap that key under a KMS-held key, so rotation re-wraps 60 bytes and deleting a key shreds data.
›
Circuit breaker
systems · low: Stop calling a failing dependency for a while, probe it with trial calls, and resume on recovery: fail fast instead of piling up timeouts.
›
Exponential backoff with jitter
systems · low: Retry after delays that grow geometrically and are randomized, so failed clients spread out instead of hammering a recovering service in synchronized waves.
›
Byte-pair encoding (BPE) tokenizati…
machine-learning · low: Learn a subword vocabulary by repeatedly merging the most frequent adjacent pair; byte-level BPE encodes any input losslessly with 32k-200k tokens.
›
Secrets management
security · low: Keep keys and passwords out of code and logs, give workloads short-lived identity instead of static keys, and make rotation routine.
›
Prompt caching
agentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.
›
Tool calling
agentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.
›
Hdr histogram
data-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentiles
Consistent hashing
distributed · low: Hash nodes and keys onto a ring; each key belongs to the next node clockwise, so membership changes move only about 1/n of keys.
›
Process supervision
hardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.
›
Power of two choices
networking · low: Pick two random backends and send to the less loaded one; exponentially better balance than random, with no global state and no herding.
›
Server-sent events
networking · low: One long-lived HTTP response carries text events one way; each event may carry an id, so a reconnecting client names its last one and the server resumes.
›
Mutual TLS
security · low: TLS where the client also proves a certificate key, so every connection carries a verified, rotatable machine identity.
›
GCRA
systems · low: Generic Cell Rate Algorithm: a token bucket stored as one theoretical arrival time per key, updated with one compare-and-swap; exact limits in 8 bytes.
›
Graceful draining
systems · low: On a termination signal, stop taking new work, finish in-flight work until a deadline, tell clients to reconnect elsewhere, then exit; clients resume from a token.
›
Hedged requests
systems · low: Sending a backup request after a latency percentile and taking the first answer to cut tail latency
Token bucket
systems · low: A bucket of up to b tokens refilled at rate r; requests spend tokens, enforcing an average rate while allowing bursts of b.
›
Calibration
machine-learning · low: Make predicted probabilities match observed frequencies: measure with ECE, fix post hoc with temperature, Platt or isotonic scaling on held-out data.
›
Embeddings
machine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.
›
LRU and CLOCK
systems · low: LRU evicts the least recently used entry via hash map plus linked list; CLOCK approximates it with a reference bit, so hits take no lock.
›
Cooperative scheduling
concurrency · low: Green threads/coroutines yielding at await points on a user-space scheduler
Record replay
distributed · low: Record every nondeterministic input (time, randomness, I/O, model and tool outputs, per-tick player input) and re-execute deterministically for debugging, replays and state rebuild
PRNGs (PCG, xoshiro)
numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.
›
Leases
distributed · low: A lock that expires on its own: bounded-time ownership that survives crashes and partitions, given bounded clock drift and fencing tokens on writes.
›
Write-ahead log
storage · low: Append each change to a checksummed sequential log and fsync it before touching data pages; the basis of crash durability in nearly every database.
›
Health checking
systems · low: Decide per backend whether to route to it using probes and real-traffic errors, with consecutive-count hysteresis, capped ejection and a panic fallback.
›
Sharded counters
concurrency · low: Split one hot counter into per-core or per-thread cells on separate cache lines; increments stay local and reads sum the cells.
›
Event deduplication window
distributed · low: Keep the ids of recently accepted events for a time window and drop repeats; memory stays bounded by rotating time buckets instead of per-entry timers.
›
Idempotency keys
finance · low: Client-chosen unique key per logical operation, stored with a request fingerprint and the final response, so retries replay the first result instead of acting twice.
›
HTTP/1.1 message parsing
networking · low: Parse HTTP/1.1 requests and responses incrementally from a byte stream: RFC 9112 body-length rules, chunked decoding and the strictness that stops request smuggling.
›
HTTP/2
networking · low: Binary multiplexed framing for HTTP over one TCP connection: streams, per-stream and per-connection credit windows, HPACK header compression and the limits that contain abuse.
›
Trie url routing
networking · low: Radix-tree HTTP routers with params and wildcards; matching priority
Connection pooling
systems · low: Reuse and multiplex backend connections with bounded pools, checkout queues and health eviction
Code coverage instrumentation
compilers · low: Insert counters into compiled code to record which blocks, edges or lines ran; a spanning tree of the control-flow graph cuts the counters needed.
›
Fast hash functions
data-structures · low: Non-cryptographic hashes built from 64×64→128-bit multiplies and xor-shifts; pick by key size, trust level and whether the hash is persisted.
›
Sanitizers
security · low: ASan/UBSan/TSan shadow memory and instrumentation to catch memory bugs
Object storage
cloud · low: S3-compatible blob storage at cents per GB-month with 11 nines durability; pick by egress price, request price and latency, not by storage price alone.
›
Copy on write snapshots
storage · low: Point-in-time snapshots by sharing pages/extents and copying only on write
Failure bisection
search-sort · low: Binary search over commits, batches or inputs to isolate a failure
Transparent interception
networking · low: Redirect traffic to a local proxy (iptables TPROXY/REDIRECT, eBPF) without app changes
Bayesian rate estimation
statistics · low: Estimate a conversion or event rate from few observations with a Beta-Binomial or Gamma-Poisson update: two counters, an honest interval, and P(B beats A) directly.
›
Linear and logistic regression
machine-learning · low: Fit a weighted sum of features to a number (least squares) or a probability (logistic); the baseline every model must beat.
›
Transformer block
ml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
SIMD programming
hardware-os · low: Process 4-16 lanes per instruction with AVX2, AVX-512 or NEON via Rust std::arch, with runtime dispatch and a portable fallback.
›
Scalar quantization
search-sort · low: Per-dimension int8/binary quantization of vectors with rescoring
X509 certificates
security · low: Certificate chains, path validation, SANs, revocation and short-lived issuance
Hash aggregation
storage · low: GROUP BY via hash tables with partitioning and spill to disk
Time partitioning
storage · low: Cut a table into fixed-interval time blocks so queries read only overlapping blocks and retention drops a whole block as one metadata change.
›
Message sequence numbers
distributed · low: A per-stream counter on every message lets the receiver detect loss, duplicates and reordering, ack cheaply and resume after reconnect with "send from N".
›
Publish subscribe event bus
systems · low: In-process or on-box topic bus decoupling producers and consumers with bounded queues
DNS message format and client looku…
networking · low: Binary query/response format of DNS (RFC 1035) and how a stub client uses it: record types, name compression, UDP/TCP/EDNS sizes, TTL caching.
›
ECDSA signatures
security · low: The elliptic-curve signature standardised in FIPS 186-5 (P-256) and used by secp256k1 ledgers; 64-byte signatures, but a repeated or biased nonce leaks the private key.
›
JSON Web Token (JWT)
security · low: A signed, URL-safe token carrying claims; the verifier's job is the checklist (pinned algorithm, key by kid, exp, aud, iss), not the format.
›
Cron scheduling
systems · low: Cron expression parsing and next-fire-time computation, with catch-up and time-zone rules
Ebpf
hardware-os · low: Verified in-kernel programs on hooks (kprobes, XDP, tc) with maps
Ptrace process control
hardware-os · low: Ptrace: attach, read and write registers and memory, single-step, intercept signals
Seccomp bpf
security · low: Syscall filtering with seccomp BPF programs
AEAD (AES-GCM, ChaCha20-Poly1305)
security · low: Authenticated encryption that encrypts and detects tampering in one call; the only kind of symmetric encryption you should use.
›
Cryptographic hashes (SHA-2, BLAKE3)
security · low: Collision-resistant fingerprints of data; SHA-256 for interoperability, BLAKE3 for speed, HMAC/HKDF for keyed uses.
›
ECDH key exchange (X25519, P-256)
security · low: Each side multiplies the other's public curve point by its own scalar and both get the same point; always validate the peer key and run the result through a KDF.
›
HKDF key derivation (extract-and-ex…
security · low: HMAC-based two-step key derivation: extract a uniform pseudorandom key from any secret, then expand it into as many context-bound keys as you need.
›
fsync, O_DSYNC and O_DIRECT
hardware-os · low: What fsync, fdatasync, O_DSYNC, O_DIRECT and F_FULLFSYNC really guarantee on Linux and macOS, and the exact call sequences for crash-safe files.
›
S3-FIFO
systems · low: Three FIFO queues (small, main, ghost) that evict one-hit wonders quickly and keep reused objects; low miss ratios with no list moves on hits.
›
Aes key wrap
security · low: AES Key Wrap (RFC 3394/5649) and AES-GCM-SIV for deterministic, authenticated wrapping of key material
Csprng
security · low: OS-backed cryptographically secure random numbers (getrandom), and when a fast PRNG is not enough
Constrained decoding
agentic-ai · low: Force LLM output to match a regex, JSON schema or grammar by masking, at every step, the tokens that would leave the language.
›
Control-flow graph
compilers · low: Split a linear instruction list into basic blocks and connect them by jumps; the graph every optimizer, SSA builder and dataflow pass walks.
›
Reference counting
compilers · low: Keep a count of owners in each object, free it when the count hits zero; deterministic and local, but pays on every copy and leaks cycles.
›
False sharing
concurrency · low: Independent variables written by different cores on one cache line force the line to bounce between cores; pad or regroup hot data to fix it.
›
Memory ordering
concurrency · low: What Relaxed, Acquire, Release and SeqCst atomics actually guarantee, what they cost on x86 and ARM, and which one each pattern needs.
›
Radix trie
data-structures · low: Compressed prefix tree for path routing, domain matching and prefix lookups
Fencing tokens
distributed · low: A number that grows with every lock grant and is checked by the protected resource, so a paused ex-holder's late write is rejected.
›
BFS and DFS
graphs · low: The two basic graph traversals; BFS gives hop distances and levels, DFS gives discovery/finish order for cycles, components and topological order.
›
Minimum spanning tree
graphs · low: Cheapest set of edges connecting all vertices; Kruskal sorts edges and joins components with union-find, Prim grows one tree, Boruvka merges in parallel rounds.
›
Union-find
graphs · low: Disjoint-set forest with union by size and path compression; merges sets and answers same-set queries in effectively constant time.
›
CPU caches and the memory hierarchy
hardware-os · low: Sizes, line widths and latencies of L1/L2/L3/DRAM on modern x86 and Apple M-series, and the data-layout rules that follow from them.
›
CRC32C checksums
hardware-os · low: The Castagnoli CRC-32 with dedicated instructions on x86 (SSE4.2) and ARMv8. It is the standard fast integrity check for storage blocks, logs and network frames.
›
Loss functions
machine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.
›
Text normalization
machine-learning · low: Rewrite messy text into one canonical form for matchers and models, or into spoken words for speech output (and back), keeping a map to the original offsets.
›
AdamW
ml-training · low: Adam's per-parameter adaptive steps with weight decay applied directly to the weights; the default optimizer for transformers and LLM pretraining.
›
Paged KV cache
ml-training · low: Store each sequence's attention keys/values in fixed-size blocks mapped through a block table, like virtual memory pages; near-zero fragmentation and copy-on-write sharing.
›
Reverse-mode automatic differentiat…
ml-training · low: Record the forward computation on a tape, then sweep it backwards once to get the gradient of a scalar loss for all inputs.
›
Token sampling
ml-training · low: Turn a vector of scores into one chosen item with temperature, top-k, top-p, min-p, repetition penalties and a seed.
›
Json rpc
networking · low: JSON-RPC 2.0 requests, notifications and batching
L-BFGS
numerics · low: Quasi-Newton minimizer that approximates the inverse Hessian from the last m gradient differences via the two-loop recursion; O(m·n) memory and work per step.
›
LU and Cholesky factorization
numerics · low: Factor A = PLU (any square matrix, partial pivoting) or A = LLᵀ (SPD) once in O(n³), then solve each right-hand side in O(n²).
›
Sparse matrices (CSR)
numerics · low: Compressed sparse row stores only nonzeros as row pointers, column indices and values; SpMV streams them once, so it is memory-bandwidth bound.
›
Finite state transducer
search-sort · low: Minimal acyclic FST mapping sorted keys to values; compact term dictionaries with prefix/fuzzy search
Constant time code
security · low: Writing secret-dependent code without branches or memory lookups on secrets; constant-time compare and select
JSON Schema validation
security · low: Compile a JSON Schema once, then check every untrusted document against it, within hard size and depth limits, and report failures as JSON Pointers.
›
OAuth 2 and OpenID Connect
security · low: Delegated authorization (OAuth 2) and login on top of it (OIDC); use authorization code + PKCE for every user-facing client.
›
Sliding-window counters
systems · low: Count events in the last W seconds with a ring of sub-bucket counters; the two-bucket weighted estimate gives rate limits in 16 bytes per key.
›
Copy for AI
Similar systems
Share the most building blocks with this one.
global-rate-limiter
41 %
serverless
38 %
reverse-etl
38 %
chat-assistant
37 %
virtual-waiting-room
36 %