Siddhant-K-code / distill
Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.
Why this job: says: persistent memory
What it does
Distill gives LLM agents persistent, deduplicated memory that survives across sessions. It prevents repeated re-learning, surfaces conflicting information before it causes mistakes, and compresses aging context so the signal stays high.
Get started
go install github.com/Siddhant-K-code/distill@latest - Maintenance
- Active
- Last commit 41 days ago
- Stars
- 198
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v0.9.1
- Released 6 months ago
- Built with
- Go
- 94% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 95% closed
- 2 still open
- Pull requests
- 77 merged
- 2 waiting
- Releases
- 13
- 13 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: download files, languages, topics and project record
Download files, v0.9.1
- Mac2 files, 33 downloads
- Windows2 files, 30 downloads
- Linux2 files, 41 downloads
Languages
- Go 94%
- Python 6%
- Shell <1%
- Makefile <1%
Topics
- ai-agents
- anthropic
- compression
- context-optimization
- deduplication
- deterministic
- developer-tools
- go
- golang
- llm
- openai
- pinecone
Project record
- JobAgent memory
- StatusListed
- Commits122
- Forks20
- Watching3
- Stars in 28 days+1
- CreatedDec 31, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026