[5-1] FTP Repositories

CMU AI Repository:

   The CMU Artificial Intelligence Repository was established by
   Carnegie Mellon University to contain public domain and freely
   distributable software, publications, and other materials of
   interest to AI researchers, educators, students, and practitioners. 
   The AI Repository currently contains more than a gigabyte of
   material and is growing steadily. 

   The AI Repository is accessible for free by anonymous FTP, AFS, and
   WWW. A selection of materials from the AI Repository is also being
   published on CD-ROM by Prime Time Freeware and is available for
   purchase by mail or fax (see [6-5] for more information).

   The AI Repository is accessible by anonymous FTP from
      ftp.cs.cmu.edu:/user/ai/            []
   by AFS (Andrew File System) from
   and by WWW from the URL   
   Be sure to read the files 0.doc and readme.txt in this directory.

   The AI Repository is still under construction, but to date, the
   AI Programming Languages and the AI Software Packages sections
   are "complete". These can be accessed in the lang/ and areas/
   subdirectories of the AI Repository. Compression and archiving
   utilities may be found in the util/ subdirectory.  Other directories,
   which are in varying states of completion, are events/ (Calendar of
   Events, Conference Calls) and pubs/ (Publications, including technical
   reports, books, mail/news archives).

   The AI Programming Languages section of the repository includes
   directories for Common Lisp, Prolog, Scheme, Smalltalk, and
   other AI-related programming languages. 

   The AI Software Packages section of the repository includes
   subdirectories for:

      agents/      Intelligent Agent Architectures 
      alife/       Artificial Life and Complex Adaptive Systems
      anneal/      Simulated Annealing
      blackbrd/    Blackboard Architectures
      bookcode/    Code From AI Textbooks
      ca/          Cellular Automata
      classics/    Classical AI Programs
      constrnt/    Constraint Processing
      dai/         Distributed AI
      discover/    Discovery and Data-Mining
      doc/         Documentation
      edu/         Educational Tools
      expert/      Expert Systems/Production Systems
      faq/         Frequently Asked Questions
      fuzzy/       Fuzzy Logic
      games/       Game Playing
      genetic/     Genetic Algorithms, Genetic Programming, 
		   Evolutionary Programming 
      icot/        ICOT Free Software
      kr/          Knowledge Representation, Semantic Nets, Frames, ...
      learning/    Machine Learning
      misc/        Miscellaneous AI
      music/       Music
      neural/      Neural Networks, Connectionist Systems, Neural Systems
      nlp/         Natural Language Processing (Natural Language
		   Understanding, Natural Language Generation, Parsing,
		   Morphology, Machine Translation)
      planning/    Planning, Plan Recognition
      reasonng/    Reasoning (Analogical Reasoning, Case Based Reasoning,
		   Defeasible Reasoning, Legal Reasoning, Medical Reasoning, 
		   Probabilistic Reasoning, Qualitative Reasoning,
		   Temporal Reasoning, Theorem Proving/Automated Reasoning,
		   Truth Maintenance) 
      robotics/    Robotics
      search/      Search
      speech/      Speech Recognition and Synthesis
      testbeds/    Planning/Agent Testbeds
      vision/      Computer Vision

   The repository has standardized on using 'tar' for producing
   archives of files and 'gzip' for compression.

   To search the keyword index by mail, send a message to:
   with one or more lines containing calls to the keys command, such as:
      keys lisp iteration
   in the message body.  Keywords may be regular expressions and are
   compared with the index in a case-insensitive conjunctive fashion.  
   You'll get a response by return mail. Do not include anything else in 
   the Subject line of the message or in the message body.  For help on
   the query mail server, include: 

   A Mosaic interface to the keyword searching program is accessible
   through the URL

   We plan on making the source code (including indexes) to
   this keyword searching program available, as soon as it is stable.

   We hope to eventually have a fully automated calendar of events,
   an expanded AI Publications directory, mailing list and newsgroup
   archives, and much much more. 

   Contributions of software and other materials are always welcome but
   must be accompanied by an unambiguous copyright statement that grants
   permission for free use, copying, and distribution -- either a
   declaration by the author that the materials are in the public domain,
   that the materials are subject to the GNU General Public License (cite
   version), or that the materials are subject to copyright, but the
   copyright holder grants permission for free use, copying, and
   distribution. (We will tell you if the copying permissions are too
   restrictive for us to include the materials in the repository.)
   Inclusion of materials in the repository does not modify their
   copyright status in any way. Materials may be placed in:
   When you put anything in this directory, please send mail to
   giving us permission to distribute the files, and state whether
   this permission is just for the AI Repository, or also includes
   publication on the CD-ROM version (Prime Time Freeware for AI).
   We would also appreciate if you would include a 0.doc file for your
   package; see /user/ai/new/package.doc for a template. (If you don't
   have the time to write your own, we can write it for you based on
   the information in your package.)

   For more information on the CMU AI Repository, please send mail to
   Mark Kantrowitz <AI.Repository@cs.cmu.edu>. 

   Known mirrors:
     + Lisp Section 

Ada Repository:

   The Ada Repository on wsmr-simtel20.army.mil (mailing list
   ada-sw@wsmr-simtel20.army.mil) contains a directory of AI programs in
   PD2:<ADA.AI>*.*. A somewhat easier to access copy of the archives is
   available as wuarchive.wustl.edu:/mirrors/ada/ai/.

UCLA Artificial Life Depository:

   ftp.cognet.ucla.edu:/pub/alife/ []

   Repository of papers, articles, tech reports, software and other items of
   interest to Artificial Life researchers. It includes an archive of
   past postings to the alife mailing list, alife@cognet.ucla.edu (send
   mail to alife-request@cognet.ucla.edu to be added to the list).

Artificial Life Online and the Artificial Life BBS:

   Sponsored by MIT Press and the Santa Fe Institute, Artificial Life
   Online and the Artificial Life BBS is intended to be a central
   information collection and distribution site on the Internet for any
   and all aspects of the Artificial Life endeavor.

   A special feature of the BBS is a collection of 40 or so local
   newsgroups dedicated to a wide variety of topics in Artificial Life.

   Artificial Life Online is accessible by anonymous ftp from
      alife.santafe.edu:/pub/ []
   by World-Wide Web from
   and by Gopher from

   To access the Alife Online BBS (ALBBS) by telnet, telnet to
   alife.santafe.edu and login as "bbs". You will find yourself in a
   specially constructed UNIX shell within which either BBS menu commands
   or UNIX commands can be used to browse around in the system. Run the
   "account" program to set up a local account. These accounts will
   initially be provided free of charge, but they will eventually have to
   charge a nominal fee in order to cover operating expenses (on the
   order of $15-$25 per year). Subscribers to the Artificial Life Journal
   from MIT Press will have this fee waived. Once you have an account on
   alife.santafe.edu, you can telnet to alife.santafe.edu and login as
   yourself. You do not have to create an account to use the ALBBS via
   telnet -- you can simply login as "bbs" and browse through the system
   using the BBS commands.

   Please send suggestions and questions about the Alife Online/BBS
   system to feedback@alife.santafe.edu.

Artificial Life:

Computational Linguistics Paper Archive:

   Papers related to computation and language (computational linguistics, 
   natural language processing, speech processing, and related fields) 
   may be submitted to and obtained from the CMP-LG email server, which
   also maintains a subscription list for automatic daily notification of
   newly submitted papers. For information about the server, send mail to
   with Subject line
   or access the WWW URL 
   The papers are also accessible by anonymous ftp to
   For more information, send mail to Stuart Shieber <shieber@das.harvard.edu>.

Consortium for Lexical Research:
   clr.nmsu.edu:/CLR/ []

   Archive containing a variety of programs and data files related to
   natural language processing research, with a particular focus on
   lexical research. The file 00README.clr.site is a good place to start.
   See the file catalog or catalog.ps for a listing of the contents of
   the archive. Long descriptions are in the info/ subdirectory.
   Materials for paid-up members of the Consortium are in the
   members-only/ subdirectory. Public materials include the Alvey Natural
   Language Tools, Sowa's Conceptual Graph parser implemented in YACC by
   Maurice Pagnucco, a morphological parsing lexicon of English, a
   phonological rule compiler for PC-KIMMO, C source code for the NIST
   SGML parser, PC-KIMMO sources, the 1911 Roget Thesaurus, and a variety
   of word lists (including English, Dutch, and male/female/last names).
   Comments and questions may be directed to lexical@nmsu.edu.

   There are also some materials in clr.nmsu.edu:/pub/ unrelated to
   the archive.   

FJ Repository:

   The FJ Repository contains freeware from Japan (FJ = "From Japan"). 
   The fj.sources subdirectory is a good place to look for free
   software from Japan. Some files in the repository may contain
   Kana and Kanji characters. The repository is available by
   anonymous ftp from 
      utsun.s.u-tokyo.ac.jp:/fj/fj.sources []
   The file Index contains an index of all the files in each volume.
   Files of particular interest include:
      v07/786:  Portable Prolog for Common Lisp
      v25/2577: General-Purpose Fuzzy Inference Library Ver. 3.0 (1/1)

Fuzzy Logic Repositories:

   ntia.its.bldrdoc.gov:/pub/fuzzy/ [] contains information
   concerning fuzzy logic, including bibliographies (bib/), product 
   descriptions and demo versions (com/), machine readable published
   papers (lit/), miscellaneous information, documents and reports (txt/), 
   and programs, code and compilers (prog/). You may download new items 
   into the new/ subdirectory. If you deposit anything in new/, please 
   inform fuzzy@its.bldrdoc.gov. The repository is maintained by 
   Timothy Butler, tim@its.bldrdoc.gov. The Fuzzy Logic Repository is also 
   accessible through a mail server, rnalib@its.bldrdoc.gov. For help on 
   using the server, send mail to the server with the following line in 
   the body of the message:
     @@ help
   Other commands available include index, list, find, send, and credits.

   Ostfold Regional College in Norway recently started a ftp site
   for material related to fuzzy logic, ftp.dhhalden.no:/pub/Fuzzy/ 
   []. Material to be included in the archive (e.g., 
   papers and code) may be placed in the upload/ directory. Now holds the 
   files from Togai's mail-server, and other files from Timothy Butler's 
   site ntia.its.bldrdoc.gov. It also includes some demo programs. Send
   email to Asgeir Osterhus, <asgeiro@dhhalden.no>.

   Togai InfraLogic, Inc. (TIL) also runs a fuzzy logic email server
   which contains demo versions of some of their software, fuzzy logic
   bibliographies, conference announcements, a short introduction to
   fuzzy logic, copies of the company newsletter, archives of
   comp.ai.fuzzy, and so on. See the entry in the answer to question
   [1-7] for more information on the company. To get started with the
   fuzzy logic email server, send a message with NO SUBJECT LINE to
   fuzzy-server@til.com, containing just the word "help" in the message
   body.  The server will reply with a set of instructions.     Please
   address any comments, questions or requests to either erik@til.com or
   tanaka@til.com. Most of the contents of the TIL server is mirrored at
   Tim Butler's fuzzy logic ftp repository at ntia.its.bldrdoc.gov and at
   Ostfold ftp repository at ftp.dhhalden.no.  For more information,
   write to Togai InfraLogic, Inc., 5 Vanderbilt, Irvine, CA 92718 or
   call 714-975-8522.

   The Aptronix FuzzyNet files are available through an email
   server. Send email to fuzzynet@aptronix.com with "help"
   in the message body to get instructions on how to retrieve files.
   "catalog" or "index" will get you a listing of available files.
   (You can also connect to the FuzzyNet repository by modem to Aptronix
   FuzzyNet 408-428-1883 N/8/1 1200-19,200 baud.) Files on the server
   include descriptions of fuzzy logic applications (e.g., washing
   machines, camera focusing, air conditioning), introductory materials,
   Fide related information, archives of comp.ai.fuzzy, etc.     If you'd
   like to have a file included in the FuzzyNet server (e.g., moderate
   length technical reports), send email to Scott Irwin

Genetic Algorithms:

   The Genetic Algorithms Repository is accessible by anonymous ftp as
   It includes past copies of the genetic algorithms digest in 
   some information files in
   and some software in 

   The information files includes Nici Schraudolph's survey of free and
   commercial GA software (send email to <schraudo@cs.ucsd.edu> to add to
   the list).

   The software includes GAC (a simple GA written in C), GAL (a simple GA
   written in Common Lisp), GAucsd, GECO (a Common Lisp toolbox for
   constructing genetic algorithms), GENESIS, GENOCOP, Paragenesis (a
   parallel version of GENESIS that runs on the CM-200), SGA-C (a C
   implementation/extension of Goldberg's SGA system).

Genetic Programming:

   The Genetic Programming Repository is located at
      ftp.cc.utexas.edu:/pub/genetic-programming/ []. It
   contains the archives of the genetic programming mailing list
   (including the GP FAQ posting), papers and source code. The source
   code includes the GP implementation from Koza's book and some related
   systems. Some of the GP packages available include GPQUICK,
   Gepetto, GPCplus, and SGPC. 

   Adam Fraser <a.fraser@eee.salford.ac.uk> has produced a html
   version of the GP FAQ and made it available from his Web page,

UC/Irvine (UCI) AI/Machine Learning Repository:

   ftp.ics.uci.edu has a variety of AI-related materials, with a special
   focus on machine learning. For example,
   contains over 80 benchmark data sets for classifier systems (30mb).

   Files may also be retrieved by email using the archive server
   archive-server@ics.uci.edu. Commands to the server should be given
   in the message body. Some commands are:
        send <archive> <file>
        find <archive> <string>
   The help command replies with a useful help message.

   Site Librarian: Patrick M. Murphy (ml-repository@ics.uci.edu)
   Off-Site Assistant: David W. Aha (aha@cs.jhu.edu)

Machine Learning:

   Various programs (e.g., ID3) and publications related to machine
   learning are available by anonymous ftp from the machine
   learning group (under Raymond Mooney) at UT-Austin, at
   Subdirectories include 
      ml-course information and homeworks from a graduate course
                     in machine learning taught by Dr. Mooney. Homeworks
                     include "miniatures" of various machine learning
                     systems written in Common Lisp.
      ml-code   Common Lisp code corresponding to the assignments
                     for the course in the ml-course directory.
      ml-progs  More "research-level" versions of inductive
                     classification algorithms and software for automated
                     experiments that generation learning curves that
                     compare several systems. 
      papers            Publications producted by the machine learning
                     research group.

Machine Learning Algorithms Implemented in Prolog:

   In 1988 the Special Interest Group on Machine Learning of the German
   Society for Computer Science (GI e.V.) decided to establish a library
   of PROLOG implementations of Machine Learning algorithms. The library
   includes - amongst others - PROLOG implementations of Winston's arch, 
   Becker's AQ-PROLOG, Fisher's COBWEB, Brazdil's generation of 
   discriminations from derivation trees, Quinlan's ID3, FOIL, IDT,
   substitution matching, explanation based generalization, inverse 
   resolution, and Mitchell's version spaces algorithm. 
   All algorithms are written in Edinburgh Prolog syntax. Most of the
   algorithms are copyleft under the GNU General Public License. 
   The programs are currently available via anonymous ftp-server from
   the GMD: 

        ftp.gmd.de:/gmd/mlt/ML-Program-Library/ []

   They are also available by surface mail from Thomas Hoppe, 
   Projektgruppe KIT, Technische Universitaet Berlin, Franklinstr. 28/29,
   10629 Berlin, Germany. Files will be distributed via MS-DOS formated
   3.5 inch floppy (double, high and extra-high density),  which should
   be included with your request. You can also get them by sending an email
   message to Thomas Hoppe (see below).

   Send additional PROLOG implementations of Machine Learning
   Algorithms, complaints about them and detected bugs or problems
   to Thomas Hoppe, <hoppet@cs.tu-berlin.de>. Send suggestions and
   complaints about the ftp library to Werner Emde, Gesellschaft
   fuer Mathematik und Datenverarbeitung, Bonn, <emde@gmd.de>. 

   The directory ftp.gmd.de:/MachineLearning/ contains additional
   machine learning publications, data, and software, primarily related
   to the European ESPRIT projects Machine Learning Toolbox (MLT) and
   Inductive Logic Programming (ILP), the European Network of Excellence
   in Machine Learning (MLnet) and the Inductive Logic Programming
   Pan-European Scientific Network (ILPnet). It includes the source code
   of Stephen Muggleton's and Cao Feng's GOLEM learning system (in
   /MachineLearning/ILP/public/software/golem) and a BibTex file with
   around 325 entries of articles related to ILP (in
   /MachineLearning/ILP/public/bib). For more information, send mail to
   Marcus Luebbe <ml-archive@gmd.de>.

CMU Simulator Collection:

   The CMU Simulator Collection is available by anonymous ftp from 
   ftp.cs.cmu.edu [] in the directory
   The collection includes Lisp and C implementations of Scott
   Fahlman's Cascade Correlation algorithm, Scott Fahlman's
   Quickprop variation on the back-propagation algorithm, and Scott
   Fahlman's Recurrent Cascade-Correlation simulator. The collection also
   includes Aspririn/Migraines and Tesauro. The neural network benchmark
   collection is available in 
   The data sets include the NETtalk data, a vowel recognition
   task, and several others.
   The archives of the connectionists mailing list are kept in
   along with a Lisp implementation of a backprop simulator. For more
   information, write to neural-bench@cs.cmu.edu.

Funic Neural FTP Archive Site:

   The Finnish University maintains an archive site containing a large
   collection of neural network papers and public domain software
   gathered from FTP sites in the US. The files are available by
   anonymous ftp from funic.funet.fi:/pub/sci/neural/ [].
   (Also know as ftp.funet.fi, nic.funet.fi.)  See the file 01README for
   details. A list of mirrored ftp sites is in 04Neural_FTP_Sites.  For
   further information, contact neural-adm@funic.funet.fi or Marko
   Gronroos <magi@funic.funet.fi> (or <magi@utu.fi>).

OSU Neuroprose:
   archive.cis.ohio-state.edu:/pub/neuroprose/   []

   This directory contains technical reports as a public service to the
   connectionist and neural network scientific community which has an
   organized mailing list (for info: connectionists-request@cs.cmu.edu)

UKaiserslautern Neural/Fuzzy Repository:

   The University of Kaiserslautern has set up a ftp server for reports
   and software related to its neural networks and fuzzy logic projects,
   including the MOBOT, SPIN, and ALBATROSS projects.  Programs currently
   available include Joerg Bruske's neural fuzzy decision system
   SPIN-NFDS and Herman Keuchel's unsupervised clustering system.  Most
   of the ready-to-run programs were written for the Apple Macintosh.
   Sources for the "kernel" of the programs are available by ftp, written
   in Pascal.  The user-interface code is also available upon request.
   Some of the documentation is in German.  The papers and software are
   available from 
   Some papers and software are also available from 
   For more information, contact Uwe R. Zimmer <uzimmer@informatik.uni-kl.de>. 

NL Software Registry:

   The Natural Language Software Registry is a catalogue of software
   implementing core natural language processing techniques, whether
   available on a commercial or noncommercial basis. Some of the topics
   listed include speech signal processing, morphological analysis,
   parsers, natural language generation systems, and knowledge
   representation systems. The second edition of the catalog contains
   more than 100 descriptions of natural language processing software.
   The catalogue is available from the German Research Institute for
   Artificial Intelligence (DFKI) in Saarbruecken (Germany) by anonymous
   ftp to 
   www to
   email to registry@dfki.uni-sb.de, or physical mail to NL Software
   Registry, Deutsches Forschungszentrum fuer Kuenstliche Intelligenz,
   Stuhlsatzenhausweg 3, D-W-6600 Saarbruecken, Germany, or by telephone
   to +49 (681) 303-5282.  Copies are also available from
   If you'd like to include your NLP software in the registry, return
   the questionnaire which is available from the ftp sites.

Essex ROBOTS Archive:
   Contains robotics related information.


Miscellaneous AI:

   Some miscellaneous AI programs may be found on ftp.uu.net:/pub/ai/
   Most are mirrors of programs available at other sites.

   AI_ATTIC is an anonymous ftp collection of classic AI programs and
   other information maintained by the University of Texas at Austin.  It
   includes Parry, Adventure, Shrdlu, Doctor, Eliza, Animals, Trek, Zork,
   Babbler, Jive, and some AI-related programming languages.     This
   archive is available by anonymous ftp from ftp.cc.utexas.edu
   (bongo.cc.utexas.edu, in the directory /pub/AI_ATTIC.
   For more information, contact atticmaster@bongo.cc.utexas.edu.

   The QWERTZ toolbox, a library of Standard ML modules with an emphasis
   on symbolic Artificial Intelligence programming, (including
   implementations of heuristic search and an ATMS reason maintenance
   system) may be obtained by anonymous ftp from
   For more information, write to Tom Gordon <thomas.gordon@gmd.de>.
Go Back Up

Go To Previous

Go To Next