Connect your Claude / AI to 2,500+ algorithms, data structures and systems

mhtirogla is an MCP server that your AI calls while it designs and builds. Name a system and you get its component graph: every technique and primitive it is built from, with alternatives. Every page opens with a one-minute overview (the problem, how it works) and goes on to the deep dive: code, complexity, pitfalls, efficiency and the libraries that implement it.

How it works

  1. Connect. claude mcp add --transport http mhtirogla https://mhtirogla.ai/mcp
  2. Say what you want to build. "A news harvester for every RSS feed", "a chess engine", "an inference server for an open model". Your AI finds the matching systems and the parts each one needs.
  3. Let your coding agent execute our specs. It builds the system in small tested steps, citing the pages it used.

API docs: tools, HTTP endpoints and an example call →

What your AI gets for a chess engine

When your AI names a system, mhtirogla returns its component graph: the techniques it needs (middle) and the primitives they are built on (right). Every box links to its page; dashed boxes have no page yet.

See all systems →
SystemTechniques · 6Primitives · 20 chess-engine Alpha-beta searchgame-ai · medium: Minimax that skips branches which cannot change the result; with iterative deepening, PVS and aspiration windows it is the core of classical adversarial search.Parallel tree searchgame-ai · medium: Search one game tree on many threads: shared lossy transposition table (Lazy SMP), split points (YBWC), virtual loss for MCTSRetrograde analysisgame-ai · medium: Solve a finite game backwards from terminal states; compact state indexing and compressed win/draw/loss and distance tablesSequential probability ratio teststatistics · medium: Add up the log-likelihood ratio per observation and stop when it crosses a fixed bound; the least data of any test with the same error rates (for two point hypotheses).Monte Carlo tree searchgame-ai · medium: Grows a search tree one simulation at a time, picking visits by a bandit rule (UCT or PUCT) and backing up averages; the search behind AlphaZero.Multi-armed banditsmachine-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.Candidate ordering and pruninggame-ai · low: The heuristics that make alpha-beta and branch-and-bound fast: try likely-best candidates first (TT, captures, killers, history) and skip or reduce the rest (null move, LMR, futility).Search time managementgame-ai · low: Allocate thinking time per move from clock, increment and search instabilityTransposition tablegame-ai · low: A fixed-size, lossy hash table of search results keyed by a state hash; gives ordering and cutoffs for repeated states, shared lock-free between threads.Zobrist hashinggame-ai · low: A state's hash is the XOR of one random 64-bit key per (item, slot) fact that holds in it, updated in a few XORs per change.Memory orderingconcurrency · low: What Relaxed, Acquire, Release and SeqCst atomics actually guarantee, what they cost on x86 and ARM, and which one each pattern needs.Huffman codingcompression · low: Optimal prefix code with whole-bit codeword lengths; table-driven decoding at about one symbol per few cycles, the entropy stage of DEFLATE, JPEG and zstd literals.Compact state encodingdata-structures · low: Pack a game position into a few fixed bytes (24 for chess: occupancy bitboard plus nibbles) for training data and dedupeBitboardsgame-ai · low: One 64-bit word per set of up to 64 items, so set algebra becomes shifts, ANDs and table lookups; magic bitboards give ray queries in one multiply.BFS and DFSgraphs · low: The two basic graph traversals; BFS gives hop distances and levels, DFS gives discovery/finish order for cycles, components and topological order.Loglikelihood scoringmachine-learning · low: Scoring choices by summed token log-probabilities, normalization by length, perplexity computationBayesian rate estimationstatistics · 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.PRNGs (PCG, xoshiro)numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.Evaluation functionsgame-ai · low: Score a game state without search: weighted features or lookup tables, interpolated by game phase; learned evaluators are variantsNNUE incremental evaluationgame-ai · low: Efficiently updatable neural network: a huge sparse first layer whose output (the accumulator) is patched per move, then tiny int8 layers; fast neural eval.SIMD programminghardware-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.Virtual memory and the TLBhardware-os · low: How page tables and TLBs translate every address, what TLB reach means, and when 2 MiB or 1 GiB huge pages pay off on Linux.+ 4 more primitives

Get Pro access

Free
€0forever

Search and read the library.

Start free

Included:

  • Search across all systems and pages
  • Overviews, How it works, Code, Complexity, Variants, Sources
  • Documentation requests
  • About 100 calls per day
Pro monthly
€20/ month

Billed monthly, cancel any time.

Get Pro monthly

Everything in Free, plus:

  • System blueprints: every part a system needs
  • Design questions with recommended answers
  • Efficiency, Implementation notes, Pitfalls, In production
  • Library verdicts, live health, security advisories
  • Build bundle for your AI
  • Higher limits and commercial use
Early-access deal · −50 %
Pro yearly
€16€8/ month

Billed €96 a year instead of €192: early-access deal until 15 Nov.

Get Pro yearly

Everything in Pro monthly:

  • Same features, billed once a year
  • 60 % less than monthly during the deal

Early access until 15 Nov 2026: everything is free. After that, Free stays free and Pro features need Pro.

Compare plans →

Missing something?

Ask for an algorithm, technique or system; repeats count as votes. Request a topic →