ForgeSight
Instrument any AI agent in a few lines — then ship traces, cost, metrics, evals, budgets, and a tamper-evident audit trail to any backend by changing one line of config. OpenTelemetry-first. Vendor-neutral. Never an agent-code change.
▶️ See the 30-second demo — instrument an agent and watch the trace, cost, and a verified tamper-evident audit trail appear.
forgesight is the batteries-included facade — the package most people install.
pip install "forgesight[otel]"
import forgesight
from forgesight import telemetry
forgesight.configure(exporters=["otel"]) # pick a backend by name — that's it
with telemetry.agent_run("pr-reviewer", version="2.1.0", metadata={"team": "platform"}) as run:
with run.llm_call("anthropic", "claude-sonnet-4-5") as call:
resp = await client.messages.create(...)
call.record_usage(input=resp.usage.input_tokens, output=resp.usage.output_tokens)
with run.tool_call("github_get_diff"):
diff = gh.get_diff(pr)
Cost, token usage, trace nesting, metrics, and multi-backend fan-out come for free. Swap
otel → langfuse, datadog, clickhouse, prometheus — the agent code never moves.
What you get
- 🔌 Vendor-neutral. The core depends on no backend or model-provider SDK. Backends are packages you install and select by config.
- 📐 OpenTelemetry-first. GenAI semantic conventions, so any OTLP backend works with no dedicated package.
- 💰 Cost built in. Token usage → USD via a pluggable pricing table — the same number everywhere — plus live attribution by team and pre-call budget projection.
- 🚦 Non-blocking & fault-isolated. Export runs on a background worker; a backend outage never breaks a run.
- 🔒 Secure by default. Content capture is opt-in; redaction runs before export.
- 🧾 Accountability. A tamper-evident, hash-chained audit trail with a compliance query/export surface.
Install backends & integrations as extras
pip install "forgesight[otel]" # one backend (OTLP → any OTel platform)
pip install "forgesight[otel,langfuse,datadog]" # several
pip install "forgesight[all]" # everything except the heavy CrewAI tree
Extras: otel · prometheus · langfuse · clickhouse · datadog · mcp · fastapi ·
github · governance · eval · registry · audit · adapters-langgraph ·
adapters-crewai. Installing a package enables a backend; config selects it.
Docs
- README & guides — full docs, playbooks, runbooks
- Quick start · Run locally with Docker · Examples
License
Metadata
Release files for forgesight 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| forgesight-0.1.1.tar.gz | 5.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| forgesight-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.6 kB
Release files / forgesight-0.1.1.tar.gz
| Download URL | forgesight-0.1.1.tar.gz |
|---|---|
| Size | 5.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5c7d8a0cf6547760a913e4e403397644cc4875129a35aba7835d5dc55ae6ada2
|
|
BLAKE2b-256 checksum How to use checksums |
a5a2758b17a354524c75cae5a9dfdab92bfc576296fba511fb7615b77cc293b0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / forgesight-0.1.1-py3-none-any.whl
| Download URL | forgesight-0.1.1-py3-none-any.whl |
|---|---|
| Size | 4.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a45efc1b2188e6bba6f09df3da47227a3ab01799dd0b3ea85b915ba7c652bb5b
|
|
BLAKE2b-256 checksum How to use checksums |
7fdd1aecfb5fffc5b92376a2ca190690107b66314067ec33f6e3af163b662682
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|