A programming language for AI agents
Code an agent writes. Limits you can read.
Every Aleph file states what it may touch, carries its own tests and answers mistakes in JSON a model can act on. You approve a program by reading three lines, not three hundred.
Rust compiler, C backend, no runtime dependencies. Open source on GitHub.
$ aleph explain words.aphcapabilities: fs.read "data"
words: pure · 1 example
main: effectful · calls words
words: pure · 1 example
main: effectful · calls words
$ aleph check (without the use line)"code":"C001", "node":"n7",
"msg":"missing capability",
"expected":"fs.read"
"msg":"missing capability",
"expected":"fs.read"
Read it in order, or not
Five ways into Aleph.
- 01The story →Four chapters after Borges: Aleph, Tlön, Orbis Tertius, Uqbar. What the language is, told as the places it is named after.
- 02Compare →The same three programs in Aleph, Python and C, with their measured sizes. Aleph is not always shorter.
- 03Numbers →What has been measured so far: speed, tests, the chronicle of the project, and what is still a placeholder.
- 04Method →How a language for agents is being built by agents: hypotheses, the loop, verification and limits.
- 05Docs →Install the compiler, learn the language, and give your agent the whole spec in under 2,000 tokens.
Epilogue
What it sees is simultaneous. What you read is successive.
That was the narrator’s despair: language unrolls in a line what the eye took in at once. Aleph splits the work. The agent holds the whole file; you read three lines of aleph explain. To begin, give your agent the spec.
One file, generated from the compiler's own tables so it never drifts: keywords, builtins with their types and capabilities, diagnostics and ten examples that pass check.
$ cargo install --git https://github.com/qursor-it/aleph alephc
$ aleph llms > context.txt
$ aleph check words.aph && aleph build words.aph -o words
$ ./words
3